moving from hub to function (#127)
* Adding content * Update en.json * Update README.md * Update TRANSLATIONS.md * Adding lesson tempolates * Fixing code files with each others code in * Update README.md * Adding lesson 16 * Adding virtual camera * Adding Wio Terminal camera capture * Adding wio terminal code * Adding SBC classification to lesson 16 * Adding challenge, review and assignment * Adding images and using new Azure icons * Update README.md * Update iot-reference-architecture.png * Adding structure for JulyOT links * Removing icons * Sketchnotes! * Create lesson-1.png * Starting on lesson 18 * Updated sketch * Adding virtual distance sensor * Adding Wio Terminal image classification * Update README.md * Adding structure for project 6 and wio terminal distance sensor * Adding some of the smart timer stuff * Updating sketchnotes * Adding virtual device speech to text * Adding chapter 21 * Language tweaks * Lesson 22 stuff * Update en.json * Bumping seeed libraries * Adding functions lab to lesson 22 * Almost done with LUIS * Update README.md * Reverting sunlight sensor change Fixes #88 * Structure * Adding speech to text lab for Pi * Adding virtual device text to speech lab * Finishing lesson 23 * Clarifying privacy Fixes #99 * Update README.md * Update hardware.md * Update README.md * Fixing some code samples that were wrong * Adding more on translation * Adding more on translator * Update README.md * Update README.md * Adding public access to the container * First part of retail object detection * More on stock lesson * Tweaks to maps lesson * Update README.md * Update pi-sensor.md * IoT Edge install stuffs * Notes on consumer groups and not running the event monitor at the same time * Assignment for object detector * Memory notes for speech to text * Migrating LUIS to an HTTP trigger * Adding Wio Terminal speech to text * Changing smart timer to functions from hubpull/135/head
Jim Bennett
3 years ago
committed by
GitHub
parent
5e9f5fdb2f
commit
68a4535193
@ -1,9 +1,14 @@
|
||||
#
|
||||
# Compare domains
|
||||
|
||||
## Instructions
|
||||
|
||||
When you created your object detector, you had a choice of multiple domains. Compare how well they work for your stock detector, and describe which gives better results.
|
||||
|
||||
To change the domain, select the **Settings** button on the top menu, select a new domain, select the **Save changes** button, then retrain the model. Make sure you test with the new iteration of the model trained with the new domain.
|
||||
|
||||
## Rubric
|
||||
|
||||
| Criteria | Exemplary | Adequate | Needs Improvement |
|
||||
| -------- | --------- | -------- | ----------------- |
|
||||
| | | | |
|
||||
| Train the model with a different domain | Was able to change the domain and re-train the model | Was able to change the domain and re-train the model | Was unable to change the domain or re-train the model |
|
||||
| Test the model and compare the results | Was able to test the model with different domains, compare results, and describe which is better | Was able to test the model with different domains, but was unable to compare the results and describe which is better | Was unable to test the model with different domains |
|
||||
|
||||
@ -1,93 +0,0 @@
|
||||
import io
|
||||
import json
|
||||
import pyaudio
|
||||
import requests
|
||||
import time
|
||||
import wave
|
||||
|
||||
from azure.iot.device import IoTHubDeviceClient, Message
|
||||
|
||||
from grove.factory import Factory
|
||||
button = Factory.getButton('GPIO-HIGH', 5)
|
||||
|
||||
audio = pyaudio.PyAudio()
|
||||
microphone_card_number = 1
|
||||
speaker_card_number = 1
|
||||
rate = 48000
|
||||
|
||||
def capture_audio():
|
||||
stream = audio.open(format = pyaudio.paInt16,
|
||||
rate = rate,
|
||||
channels = 1,
|
||||
input_device_index = microphone_card_number,
|
||||
input = True,
|
||||
frames_per_buffer = 4096)
|
||||
|
||||
frames = []
|
||||
|
||||
while button.is_pressed():
|
||||
frames.append(stream.read(4096))
|
||||
|
||||
stream.stop_stream()
|
||||
stream.close()
|
||||
|
||||
wav_buffer = io.BytesIO()
|
||||
with wave.open(wav_buffer, 'wb') as wavefile:
|
||||
wavefile.setnchannels(1)
|
||||
wavefile.setsampwidth(audio.get_sample_size(pyaudio.paInt16))
|
||||
wavefile.setframerate(rate)
|
||||
wavefile.writeframes(b''.join(frames))
|
||||
wav_buffer.seek(0)
|
||||
|
||||
return wav_buffer
|
||||
|
||||
speech_api_key = '<key>'
|
||||
location = '<location>'
|
||||
language = '<language>'
|
||||
connection_string = '<connection_string>'
|
||||
|
||||
device_client = IoTHubDeviceClient.create_from_connection_string(connection_string)
|
||||
|
||||
print('Connecting')
|
||||
device_client.connect()
|
||||
print('Connected')
|
||||
|
||||
def get_access_token():
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_api_key
|
||||
}
|
||||
|
||||
token_endpoint = f'https://{location}.api.cognitive.microsoft.com/sts/v1.0/issuetoken'
|
||||
response = requests.post(token_endpoint, headers=headers)
|
||||
return str(response.text)
|
||||
|
||||
def convert_speech_to_text(buffer):
|
||||
url = f'https://{location}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1'
|
||||
|
||||
headers = {
|
||||
'Authorization': 'Bearer ' + get_access_token(),
|
||||
'Content-Type': f'audio/wav; codecs=audio/pcm; samplerate={rate}',
|
||||
'Accept': 'application/json;text/xml'
|
||||
}
|
||||
|
||||
params = {
|
||||
'language': language
|
||||
}
|
||||
|
||||
response = requests.post(url, headers=headers, params=params, data=buffer)
|
||||
response_json = json.loads(response.text)
|
||||
|
||||
if response_json['RecognitionStatus'] == 'Success':
|
||||
return response_json['DisplayText']
|
||||
else:
|
||||
return ''
|
||||
|
||||
while True:
|
||||
while not button.is_pressed():
|
||||
time.sleep(.1)
|
||||
|
||||
buffer = capture_audio()
|
||||
text = convert_speech_to_text(buffer)
|
||||
if len(text) > 0:
|
||||
message = Message(json.dumps({ 'speech': text }))
|
||||
device_client.send_message(message)
|
||||
@ -1,33 +0,0 @@
|
||||
import json
|
||||
import time
|
||||
from azure.cognitiveservices.speech import SpeechConfig, SpeechRecognizer
|
||||
from azure.iot.device import IoTHubDeviceClient, Message
|
||||
|
||||
speech_api_key = '<key>'
|
||||
location = '<location>'
|
||||
language = '<language>'
|
||||
connection_string = '<connection_string>'
|
||||
|
||||
device_client = IoTHubDeviceClient.create_from_connection_string(connection_string)
|
||||
|
||||
print('Connecting')
|
||||
device_client.connect()
|
||||
print('Connected')
|
||||
|
||||
recognizer_config = SpeechConfig(subscription=speech_api_key,
|
||||
region=location,
|
||||
speech_recognition_language=language)
|
||||
|
||||
recognizer = SpeechRecognizer(speech_config=recognizer_config)
|
||||
|
||||
def recognized(args):
|
||||
if len(args.result.text) > 0:
|
||||
message = Message(json.dumps({ 'speech': args.result.text }))
|
||||
device_client.send_message(message)
|
||||
|
||||
recognizer.recognized.connect(recognized)
|
||||
|
||||
recognizer.start_continuous_recognition()
|
||||
|
||||
while True:
|
||||
time.sleep(1)
|
||||
@ -0,0 +1,39 @@
|
||||
|
||||
This directory is intended for project header files.
|
||||
|
||||
A header file is a file containing C declarations and macro definitions
|
||||
to be shared between several project source files. You request the use of a
|
||||
header file in your project source file (C, C++, etc) located in `src` folder
|
||||
by including it, with the C preprocessing directive `#include'.
|
||||
|
||||
```src/main.c
|
||||
|
||||
#include "header.h"
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Including a header file produces the same results as copying the header file
|
||||
into each source file that needs it. Such copying would be time-consuming
|
||||
and error-prone. With a header file, the related declarations appear
|
||||
in only one place. If they need to be changed, they can be changed in one
|
||||
place, and programs that include the header file will automatically use the
|
||||
new version when next recompiled. The header file eliminates the labor of
|
||||
finding and changing all the copies as well as the risk that a failure to
|
||||
find one copy will result in inconsistencies within a program.
|
||||
|
||||
In C, the usual convention is to give header files names that end with `.h'.
|
||||
It is most portable to use only letters, digits, dashes, and underscores in
|
||||
header file names, and at most one dot.
|
||||
|
||||
Read more about using header files in official GCC documentation:
|
||||
|
||||
* Include Syntax
|
||||
* Include Operation
|
||||
* Once-Only Headers
|
||||
* Computed Includes
|
||||
|
||||
https://gcc.gnu.org/onlinedocs/cpp/Header-Files.html
|
||||
@ -0,0 +1,46 @@
|
||||
|
||||
This directory is intended for project specific (private) libraries.
|
||||
PlatformIO will compile them to static libraries and link into executable file.
|
||||
|
||||
The source code of each library should be placed in a an own separate directory
|
||||
("lib/your_library_name/[here are source files]").
|
||||
|
||||
For example, see a structure of the following two libraries `Foo` and `Bar`:
|
||||
|
||||
|--lib
|
||||
| |
|
||||
| |--Bar
|
||||
| | |--docs
|
||||
| | |--examples
|
||||
| | |--src
|
||||
| | |- Bar.c
|
||||
| | |- Bar.h
|
||||
| | |- library.json (optional, custom build options, etc) https://docs.platformio.org/page/librarymanager/config.html
|
||||
| |
|
||||
| |--Foo
|
||||
| | |- Foo.c
|
||||
| | |- Foo.h
|
||||
| |
|
||||
| |- README --> THIS FILE
|
||||
|
|
||||
|- platformio.ini
|
||||
|--src
|
||||
|- main.c
|
||||
|
||||
and a contents of `src/main.c`:
|
||||
```
|
||||
#include <Foo.h>
|
||||
#include <Bar.h>
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
PlatformIO Library Dependency Finder will find automatically dependent
|
||||
libraries scanning project source files.
|
||||
|
||||
More information about PlatformIO Library Dependency Finder
|
||||
- https://docs.platformio.org/page/librarymanager/ldf.html
|
||||
@ -0,0 +1,19 @@
|
||||
; PlatformIO Project Configuration File
|
||||
;
|
||||
; Build options: build flags, source filter
|
||||
; Upload options: custom upload port, speed and extra flags
|
||||
; Library options: dependencies, extra library storages
|
||||
; Advanced options: extra scripting
|
||||
;
|
||||
; Please visit documentation for the other options and examples
|
||||
; https://docs.platformio.org/page/projectconf.html
|
||||
|
||||
[env:seeed_wio_terminal]
|
||||
platform = atmelsam
|
||||
board = seeed_wio_terminal
|
||||
framework = arduino
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.0.3
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.1
|
||||
build_flags =
|
||||
-DSFUD_USING_QSPI
|
||||
@ -0,0 +1,60 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
};
|
||||
@ -0,0 +1,49 @@
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
|
||||
#include "mic.h"
|
||||
|
||||
void setup()
|
||||
{
|
||||
Serial.begin(9600);
|
||||
|
||||
while (!Serial)
|
||||
; // Wait for Serial to be ready
|
||||
|
||||
delay(1000);
|
||||
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
|
||||
mic.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
}
|
||||
|
||||
void processAudio()
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,248 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "flash_writer.h"
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
static uint16_t idx = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
||||
@ -0,0 +1,11 @@
|
||||
|
||||
This directory is intended for PlatformIO Unit Testing and project tests.
|
||||
|
||||
Unit Testing is a software testing method by which individual units of
|
||||
source code, sets of one or more MCU program modules together with associated
|
||||
control data, usage procedures, and operating procedures, are tested to
|
||||
determine whether they are fit for use. Unit testing finds problems early
|
||||
in the development cycle.
|
||||
|
||||
More information about PlatformIO Unit Testing:
|
||||
- https://docs.platformio.org/page/plus/unit-testing.html
|
||||
@ -0,0 +1,39 @@
|
||||
|
||||
This directory is intended for project header files.
|
||||
|
||||
A header file is a file containing C declarations and macro definitions
|
||||
to be shared between several project source files. You request the use of a
|
||||
header file in your project source file (C, C++, etc) located in `src` folder
|
||||
by including it, with the C preprocessing directive `#include'.
|
||||
|
||||
```src/main.c
|
||||
|
||||
#include "header.h"
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Including a header file produces the same results as copying the header file
|
||||
into each source file that needs it. Such copying would be time-consuming
|
||||
and error-prone. With a header file, the related declarations appear
|
||||
in only one place. If they need to be changed, they can be changed in one
|
||||
place, and programs that include the header file will automatically use the
|
||||
new version when next recompiled. The header file eliminates the labor of
|
||||
finding and changing all the copies as well as the risk that a failure to
|
||||
find one copy will result in inconsistencies within a program.
|
||||
|
||||
In C, the usual convention is to give header files names that end with `.h'.
|
||||
It is most portable to use only letters, digits, dashes, and underscores in
|
||||
header file names, and at most one dot.
|
||||
|
||||
Read more about using header files in official GCC documentation:
|
||||
|
||||
* Include Syntax
|
||||
* Include Operation
|
||||
* Once-Only Headers
|
||||
* Computed Includes
|
||||
|
||||
https://gcc.gnu.org/onlinedocs/cpp/Header-Files.html
|
||||
@ -0,0 +1,46 @@
|
||||
|
||||
This directory is intended for project specific (private) libraries.
|
||||
PlatformIO will compile them to static libraries and link into executable file.
|
||||
|
||||
The source code of each library should be placed in a an own separate directory
|
||||
("lib/your_library_name/[here are source files]").
|
||||
|
||||
For example, see a structure of the following two libraries `Foo` and `Bar`:
|
||||
|
||||
|--lib
|
||||
| |
|
||||
| |--Bar
|
||||
| | |--docs
|
||||
| | |--examples
|
||||
| | |--src
|
||||
| | |- Bar.c
|
||||
| | |- Bar.h
|
||||
| | |- library.json (optional, custom build options, etc) https://docs.platformio.org/page/librarymanager/config.html
|
||||
| |
|
||||
| |--Foo
|
||||
| | |- Foo.c
|
||||
| | |- Foo.h
|
||||
| |
|
||||
| |- README --> THIS FILE
|
||||
|
|
||||
|- platformio.ini
|
||||
|--src
|
||||
|- main.c
|
||||
|
||||
and a contents of `src/main.c`:
|
||||
```
|
||||
#include <Foo.h>
|
||||
#include <Bar.h>
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
PlatformIO Library Dependency Finder will find automatically dependent
|
||||
libraries scanning project source files.
|
||||
|
||||
More information about PlatformIO Library Dependency Finder
|
||||
- https://docs.platformio.org/page/librarymanager/ldf.html
|
||||
@ -0,0 +1,22 @@
|
||||
; PlatformIO Project Configuration File
|
||||
;
|
||||
; Build options: build flags, source filter
|
||||
; Upload options: custom upload port, speed and extra flags
|
||||
; Library options: dependencies, extra library storages
|
||||
; Advanced options: extra scripting
|
||||
;
|
||||
; Please visit documentation for the other options and examples
|
||||
; https://docs.platformio.org/page/projectconf.html
|
||||
|
||||
[env:seeed_wio_terminal]
|
||||
platform = atmelsam
|
||||
board = seeed_wio_terminal
|
||||
framework = arduino
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.0.3
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.1
|
||||
seeed-studio/Seeed Arduino rpcWiFi @ 1.0.5
|
||||
seeed-studio/Seeed Arduino rpcUnified @ 2.1.3
|
||||
seeed-studio/Seeed_Arduino_mbedtls @ 3.0.1
|
||||
seeed-studio/Seeed Arduino RTC @ 2.0.0
|
||||
bblanchon/ArduinoJson @ 6.17.3
|
||||
@ -0,0 +1,89 @@
|
||||
#pragma once
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
|
||||
const char *SSID = "<SSID>";
|
||||
const char *PASSWORD = "<PASSWORD>";
|
||||
|
||||
const char *SPEECH_API_KEY = "<API_KEY>";
|
||||
const char *SPEECH_LOCATION = "<LOCATION>";
|
||||
const char *LANGUAGE = "<LANGUAGE>";
|
||||
|
||||
const char *TOKEN_URL = "https://%s.api.cognitive.microsoft.com/sts/v1.0/issuetoken";
|
||||
const char *SPEECH_URL = "https://%s.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=%s";
|
||||
|
||||
const char *TOKEN_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQAueRcfuAIek/4tmDg0xQwDANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwNjCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBALVGARl56bx3KBUSGuPc4H5uoNFkFH4e7pvTCxRi4j/+z+Xb\r\n"
|
||||
"wjEz+5CipDOqjx9/jWjskL5dk7PaQkzItidsAAnDCW1leZBOIi68Lff1bjTeZgMY\r\n"
|
||||
"iwdRd3Y39b/lcGpiuP2d23W95YHkMMT8IlWosYIX0f4kYb62rphyfnAjYb/4Od99\r\n"
|
||||
"ThnhlAxGtfvSbXcBVIKCYfZgqRvV+5lReUnd1aNjRYVzPOoifgSx2fRyy1+pO1Uz\r\n"
|
||||
"aMMNnIOE71bVYW0A1hr19w7kOb0KkJXoALTDDj1ukUEDqQuBfBxReL5mXiu1O7WG\r\n"
|
||||
"0vltg0VZ/SZzctBsdBlx1BkmWYBW261KZgBivrql5ELTKKd8qgtHcLQA5fl6JB0Q\r\n"
|
||||
"gs5XDaWehN86Gps5JW8ArjGtjcWAIP+X8CQaWfaCnuRm6Bk/03PQWhgdi84qwA0s\r\n"
|
||||
"sRfFJwHUPTNSnE8EiGVk2frt0u8PG1pwSQsFuNJfcYIHEv1vOzP7uEOuDydsmCjh\r\n"
|
||||
"lxuoK2n5/2aVR3BMTu+p4+gl8alXoBycyLmj3J/PUgqD8SL5fTCUegGsdia/Sa60\r\n"
|
||||
"N2oV7vQ17wjMN+LXa2rjj/b4ZlZgXVojDmAjDwIRdDUujQu0RVsJqFLMzSIHpp2C\r\n"
|
||||
"Zp7mIoLrySay2YYBu7SiNwL95X6He2kS8eefBBHjzwW/9FxGqry57i71c2cDAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQU1cFnOsKjnfR3UltZEjgp5lVou6UwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQB2oWc93fB8esci/8esixj++N22meiGDjgF\r\n"
|
||||
"+rA2LUK5IOQOgcUSTGKSqF9lYfAxPjrqPjDCUPHCURv+26ad5P/BYtXtbmtxJWu+\r\n"
|
||||
"cS5BhMDPPeG3oPZwXRHBJFAkY4O4AF7RIAAUW6EzDflUoDHKv83zOiPfYGcpHc9s\r\n"
|
||||
"kxAInCedk7QSgXvMARjjOqdakor21DTmNIUotxo8kHv5hwRlGhBJwps6fEVi1Bt0\r\n"
|
||||
"trpM/3wYxlr473WSPUFZPgP1j519kLpWOJ8z09wxay+Br29irPcBYv0GMXlHqThy\r\n"
|
||||
"8y4m/HyTQeI2IMvMrQnwqPpY+rLIXyviI2vLoI+4xKE4Rn38ZZ8m\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
|
||||
const char *SPEECH_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQCq+mxcpjxFFB6jvh98dTFzANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwMTCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBAMedcDrkXufP7pxVm1FHLDNA9IjwHaMoaY8arqqZ4Gff4xyr\r\n"
|
||||
"RygnavXL7g12MPAx8Q6Dd9hfBzrfWxkF0Br2wIvlvkzW01naNVSkHp+OS3hL3W6n\r\n"
|
||||
"l/jYvZnVeJXjtsKYcXIf/6WtspcF5awlQ9LZJcjwaH7KoZuK+THpXCMtzD8XNVdm\r\n"
|
||||
"GW/JI0C/7U/E7evXn9XDio8SYkGSM63aLO5BtLCv092+1d4GGBSQYolRq+7Pd1kR\r\n"
|
||||
"EkWBPm0ywZ2Vb8GIS5DLrjelEkBnKCyy3B0yQud9dpVsiUeE7F5sY8Me96WVxQcb\r\n"
|
||||
"OyYdEY/j/9UpDlOG+vA+YgOvBhkKEjiqygVpP8EZoMMijephzg43b5Qi9r5UrvYo\r\n"
|
||||
"o19oR/8pf4HJNDPF0/FJwFVMW8PmCBLGstin3NE1+NeWTkGt0TzpHjgKyfaDP2tO\r\n"
|
||||
"4bCk1G7pP2kDFT7SYfc8xbgCkFQ2UCEXsaH/f5YmpLn4YPiNFCeeIida7xnfTvc4\r\n"
|
||||
"7IxyVccHHq1FzGygOqemrxEETKh8hvDR6eBdrBwmCHVgZrnAqnn93JtGyPLi6+cj\r\n"
|
||||
"WGVGtMZHwzVvX1HvSFG771sskcEjJxiQNQDQRWHEh3NxvNb7kFlAXnVdRkkvhjpR\r\n"
|
||||
"GchFhTAzqmwltdWhWDEyCMKC2x/mSZvZtlZGY+g37Y72qHzidwtyW7rBetZJAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQUDyBd16FXlduSzyvQx8J3BM5ygHYwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQAlFvNh7QgXVLAZSsNR2XRmIn9iS8OHFCBA\r\n"
|
||||
"WxKJoi8YYQafpMTkMqeuzoL3HWb1pYEipsDkhiMnrpfeYZEA7Lz7yqEEtfgHcEBs\r\n"
|
||||
"K9KcStQGGZRfmWU07hPXHnFz+5gTXqzCE2PBMlRgVUYJiA25mJPXfB00gDvGhtYa\r\n"
|
||||
"+mENwM9Bq1B9YYLyLjRtUz8cyGsdyTIG/bBM/Q9jcV8JGqMU/UjAdh1pFyTnnHEl\r\n"
|
||||
"Y59Npi7F87ZqYYJEHJM2LGD+le8VsHjgeWX2CJQko7klXvcizuZvUEDTjHaQcs2J\r\n"
|
||||
"+kPgfyMIOY1DMJ21NxOJ2xPRC/wAh/hzSBRVtoAnyuxtkZ4VjIOh\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
@ -0,0 +1,69 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <sfud.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class FlashStream : public Stream
|
||||
{
|
||||
public:
|
||||
FlashStream()
|
||||
{
|
||||
_pos = 0;
|
||||
_flash_address = 0;
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
virtual int available()
|
||||
{
|
||||
int remaining = BUFFER_SIZE - ((_flash_address - HTTP_TCP_BUFFER_SIZE) + _pos);
|
||||
int bytes_available = min(HTTP_TCP_BUFFER_SIZE, remaining);
|
||||
|
||||
if (bytes_available == 0)
|
||||
{
|
||||
bytes_available = -1;
|
||||
}
|
||||
|
||||
return bytes_available;
|
||||
}
|
||||
|
||||
virtual int read()
|
||||
{
|
||||
int retVal = _buffer[_pos++];
|
||||
|
||||
if (_pos == HTTP_TCP_BUFFER_SIZE)
|
||||
{
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
return retVal;
|
||||
}
|
||||
|
||||
virtual int peek()
|
||||
{
|
||||
return _buffer[_pos];
|
||||
}
|
||||
|
||||
private:
|
||||
void populateBuffer()
|
||||
{
|
||||
sfud_read(_flash, _flash_address, HTTP_TCP_BUFFER_SIZE, _buffer);
|
||||
_flash_address += HTTP_TCP_BUFFER_SIZE;
|
||||
_pos = 0;
|
||||
}
|
||||
|
||||
size_t _pos;
|
||||
size_t _flash_address;
|
||||
const sfud_flash *_flash;
|
||||
|
||||
byte _buffer[HTTP_TCP_BUFFER_SIZE];
|
||||
};
|
||||
@ -0,0 +1,60 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
};
|
||||
@ -0,0 +1,69 @@
|
||||
#include <Arduino.h>
|
||||
#include <rpcWiFi.h>
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "mic.h"
|
||||
#include "speech_to_text.h"
|
||||
|
||||
void connectWiFi()
|
||||
{
|
||||
while (WiFi.status() != WL_CONNECTED)
|
||||
{
|
||||
Serial.println("Connecting to WiFi..");
|
||||
WiFi.begin(SSID, PASSWORD);
|
||||
delay(500);
|
||||
}
|
||||
|
||||
Serial.println("Connected!");
|
||||
}
|
||||
|
||||
void setup()
|
||||
{
|
||||
Serial.begin(9600);
|
||||
|
||||
while (!Serial)
|
||||
; // Wait for Serial to be ready
|
||||
|
||||
delay(1000);
|
||||
|
||||
connectWiFi();
|
||||
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
|
||||
mic.init();
|
||||
|
||||
speechToText.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
}
|
||||
|
||||
void processAudio()
|
||||
{
|
||||
String text = speechToText.convertSpeechToText();
|
||||
Serial.println(text);
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,242 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_writer.h"
|
||||
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
||||
@ -0,0 +1,102 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_stream.h"
|
||||
|
||||
class SpeechToText
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_token_client.setCACert(TOKEN_CERTIFICATE);
|
||||
_speech_client.setCACert(SPEECH_CERTIFICATE);
|
||||
_access_token = getAccessToken();
|
||||
}
|
||||
|
||||
String convertSpeechToText()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, SPEECH_URL, SPEECH_LOCATION, LANGUAGE);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_speech_client, url);
|
||||
|
||||
httpClient.addHeader("Authorization", String("Bearer ") + _access_token);
|
||||
httpClient.addHeader("Content-Type", String("audio/wav; codecs=audio/pcm; samplerate=") + String(RATE));
|
||||
httpClient.addHeader("Accept", "application/json;text/xml");
|
||||
|
||||
Serial.println("Sending speech...");
|
||||
|
||||
FlashStream stream;
|
||||
int httpResponseCode = httpClient.sendRequest("POST", &stream, BUFFER_SIZE);
|
||||
|
||||
Serial.println("Speech sent!");
|
||||
|
||||
String text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
text = obj["DisplayText"].as<String>();
|
||||
}
|
||||
else if (httpResponseCode == 401)
|
||||
{
|
||||
Serial.println("Access token expired, trying again with a new token");
|
||||
_access_token = getAccessToken();
|
||||
return convertSpeechToText();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to convert text to speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return text;
|
||||
}
|
||||
|
||||
private:
|
||||
String getAccessToken()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, TOKEN_URL, SPEECH_LOCATION);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_token_client, url);
|
||||
|
||||
httpClient.addHeader("Ocp-Apim-Subscription-Key", SPEECH_API_KEY);
|
||||
int httpResultCode = httpClient.POST("{}");
|
||||
|
||||
if (httpResultCode != 200)
|
||||
{
|
||||
Serial.println("Error getting access token, trying again...");
|
||||
delay(10000);
|
||||
return getAccessToken();
|
||||
}
|
||||
|
||||
Serial.println("Got access token.");
|
||||
String result = httpClient.getString();
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
WiFiClientSecure _token_client;
|
||||
WiFiClientSecure _speech_client;
|
||||
String _access_token;
|
||||
};
|
||||
|
||||
SpeechToText speechToText;
|
||||
@ -0,0 +1,11 @@
|
||||
|
||||
This directory is intended for PlatformIO Unit Testing and project tests.
|
||||
|
||||
Unit Testing is a software testing method by which individual units of
|
||||
source code, sets of one or more MCU program modules together with associated
|
||||
control data, usage procedures, and operating procedures, are tested to
|
||||
determine whether they are fit for use. Unit testing finds problems early
|
||||
in the development cycle.
|
||||
|
||||
More information about PlatformIO Unit Testing:
|
||||
- https://docs.platformio.org/page/plus/unit-testing.html
|
||||
@ -1,3 +1,536 @@
|
||||
# Capture audio - Wio Terminal
|
||||
|
||||
Coming soon!
|
||||
In this part of the lesson, you will write code to capture audio on your Wio Terminal. Audio capture will be controlled by one of the buttons on the top of the Wio Terminal.
|
||||
|
||||
## Program the device to capture audio
|
||||
|
||||
You can capture audio from the microphone using C++ code. The Wio Terminal only has 192KB of RAM, not enough to capture more than a couple of seconds of audio. It also has 4MB of flash memory, so this can be used instead, saving captured audio to the flash memory.
|
||||
|
||||
The built-in microphone captures an analog signal, which gets converted to a digital signal that the Wio Terminal can use. When capturing audio, the data needs to be captured at the correct time - for example to capture audio at 16KHz, the audio needs to be captured exactly 16,000 times per second, with equal intervals between each sample. Rather than use your code to do this, you can use the direct memory access controller (DMAC). This is circuitry that can capture a signal from somewhere and write to memory, without interrupting your code running on the processor.
|
||||
|
||||
✅ Read more on DMA on the [direct memory access page on Wikipedia](https://wikipedia.org/wiki/Direct_memory_access).
|
||||
|
||||
|
||||
|
||||
The DMAC can capture audio from the ADC at fixed intervals, such as at 16,000 times a second for 16KHz audio. It can write this captured data to a pre-allocated memory buffer, and when this is full, make it available to your code to process. Using this memory can delay capturing audio, but you can set up multiple buffers. The DMAC writes to buffer 1, then when it's full, notifies your code to proces buffer 1, whilst the DMAC writes to buffer 2. When buffer 2 is full, it notifies your code, and goes back to writing to buffer 1. That way as long as you process each buffer in less time that it takes to fill one, you will not lose any data.
|
||||
|
||||
Once each buffer has been captured, it can be written to the flash memory. Flash memory needs to be written to using defined addresses, specifying where to write and how large to write, similar to updating an array of bytes in memory. Flash memory has granularity, meaning erase and writing operations rely not only on being of a fixed size, but aligning to that size. For example, if the granularity is 4096 bytes and you request an erase at address 4200, it could erase all the data from address 4096 to 8192. This means when you write the audio data to flash memory, it has to be in chunks of the correct size.
|
||||
|
||||
### Task - configure flash memory
|
||||
|
||||
1. Create a brand new Wio Terminal project using PlatformIO. Call this project `smart-timer`. Add code in the `setup` function to configure the serial port.
|
||||
|
||||
1. Add the following library dependencies to the `platformio.ini` file to provide access to the flash memory:
|
||||
|
||||
```ini
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.0.3
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.1
|
||||
```
|
||||
|
||||
1. Open the `main.cpp` file and add the following include directive for the flash memory library to the top of the file:
|
||||
|
||||
```cpp
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
```
|
||||
|
||||
> 🎓 SFUD stands for Serial Flash Universal Driver, and is a library designed to work with all flash memory chips
|
||||
|
||||
1. In the `setup` function, add the following code to set up the flash storage library:
|
||||
|
||||
```cpp
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
```
|
||||
|
||||
This loops until the SFUD library is initialized, then turns on fast reads. The built-in flash memory can be accessed using a Queued Serial Peripheral Interface (QSPI), a type of SPI controller that allows continuous access via a queue with minimal processor usage. This makes it faster to read and write to flash memory.
|
||||
|
||||
1. Create a new file in the `src` folder called `flash_writer.h`.
|
||||
|
||||
1. Add the following to the top of this file:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
```
|
||||
|
||||
This includes some needed header files, including the header file for the SFUD library to interact with flash memory
|
||||
|
||||
1. Define a class in this new header file called `FlashWriter`:
|
||||
|
||||
```cpp
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
|
||||
private:
|
||||
};
|
||||
```
|
||||
|
||||
1. In the `private` section, add the following code:
|
||||
|
||||
```cpp
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
```
|
||||
|
||||
This defines some fields for the buffer to use to store data before writing it to the flash memory. There is a byte array, `_sfudBuffer`, to write data to, and when this is full, the data is written to flash memory. The `_sfudBufferPos` field stores the current location to write to in this buffer, and `_sfudBufferWritePos` stores the location in flash memory to write to. `_flash` is a pointer the flash memory to write to - some microcontrollers have multiple flash memory chips.
|
||||
|
||||
1. Add the following method to the `public` section to initialize this class:
|
||||
|
||||
```cpp
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
```
|
||||
|
||||
This configures the flash memory on teh Wio Terminal to write to, and sets up the buffers based off the grain size of the flash memory. This is in an `init` method, rather than a constructor as this needs to be called after the flash memory has been set up in the `setup` function.
|
||||
|
||||
1. Add the following code to the `public` section:
|
||||
|
||||
```cpp
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This code defines methods to write bytes to the flash storage system. It works by writing to an in-memory buffer that is the right size for the flash memory, and when this is full, this is written to the flash memory, erasing any existing data at that location. There is also a `flushSfudBuffer` to write an incomplete buffer, as the data being captured won't be exact multiples of the grain size, so the end part of the data needs to be written.
|
||||
|
||||
> 💁 The end part of the data will write additional unwanted data, but this is ok as only the data needed will be read.
|
||||
|
||||
### Task - set up audio capture
|
||||
|
||||
1. Create a new file in the `src` folder called `config.h`.
|
||||
|
||||
1. Add the following to the top of this file:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
```
|
||||
|
||||
This code sets up some constants for the audio capture.
|
||||
|
||||
| Constant | Value | Description |
|
||||
| --------------------- | -----: | - |
|
||||
| RATE | 16000 | The sample rate for the audio. !6,000 is 16KHz |
|
||||
| SAMPLE_LENGTH_SECONDS | 4 | The length of audio to capture. This is set to 4 seconds. To record longer audio, increase this. |
|
||||
| SAMPLES | 64000 | The total number of audio samples that will be captured. Set to the sample rate * the number of seconds |
|
||||
| BUFFER_SIZE | 128044 | The size of the audio buffer to capture. Audio will be captured as a WAV file, which is 44 bytes of header, then 128,000 bytes of audio date (each sample is 2 bytes) |
|
||||
| ADC_BUF_LEN | 1600 | The size of the buffers to use to capture audio from the DMAC |
|
||||
|
||||
> 💁 If you find 4 seconds is too short to request a timer, you can increase the `SAMPLE_LENGTH_SECONDS` value, and all the other values will recalculate.
|
||||
|
||||
1. Create a new file in the `src` folder called `mic.h`.
|
||||
|
||||
1. Add the following to the top of this file:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_writer.h"
|
||||
```
|
||||
|
||||
This includes some needed header files, including the `config.h` and `FlashWriter` header files.
|
||||
|
||||
1. Add the following to define a `Mic` class that can capture from the microphone:
|
||||
|
||||
```cpp
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
```
|
||||
|
||||
This class currently only has a couple of fields to track if recording has started, and if a recording is ready to be used. When the DMAC is set up, it continuously writes to memory buffers, so the `_isRecording` flag determines if these should be processed or ignored. The `_isRecordingReady` flag will be set when the required 4 seconds of audio has been captured. The `_writer` field is used to save the audio data to flash memory.
|
||||
|
||||
A global variable is then declared for an instance of the `Mic` class.
|
||||
|
||||
1. Add the following code to the `private` section of the `Mic` class:
|
||||
|
||||
```cpp
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
```
|
||||
|
||||
This code defines a `configureDmaAdc` method that configures the DMAC, connecting it to the ADC and setting it to populate two different alternating buffers, `_adc_buf_0` and `_adc_buf_0`.
|
||||
|
||||
> 💁 One of the downsides of microcontroller development is the complexity of the code needed to interact with hardware, as your code runs at a very low level interacting with hardware directly. This code is more complex than what you would write for a single-board computer or desktop computer as there is no operating system to help. There are some libraries available that can simplify this, but there is still a lot of complexity.
|
||||
|
||||
1. Below this, add the following code:
|
||||
|
||||
```cpp
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
```
|
||||
|
||||
This code defines the WAV header as a struct that takes up 44 bytes of memory. It writes details to it about the audio file rate, size, and number of channels. This header is then written to the flash memory
|
||||
|
||||
1. Below this code, add the following to declare a method to be called when the audio buffers are ready to process:
|
||||
|
||||
```cpp
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The audio buffers are arrays of 16-bit integers containing the audio from the ADC. The ADC returns 12-bit unsigned values (0-1023), so these need to be converted to 16-bit signed values, and then converted into 2 bytes to be stored as raw binary data.
|
||||
|
||||
These bytes are written to the flash memory buffers. The write starts at index 44 - this is the offset from the 44 bytes written as the WAV file header. Once all the bytes needed for the required audio length have been captured, the remaing data is written to the flash memory.
|
||||
|
||||
1. In the `public` section of the `Mic` class, add the following code:
|
||||
|
||||
```cpp
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This code will be called by the DMAC to tell your code to process the buffers. It checks that there is data to process, and calls the `audioCallback` method with the relevant buffer.
|
||||
|
||||
1. Outside the class, after the `Mic mic;` declaration, add the following code:
|
||||
|
||||
```cpp
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
||||
```
|
||||
|
||||
The `DMAC_1_Handler` will be called by the DMAC when there the buffers are ready to process. This function is found by name, so just needs to exist to be called.
|
||||
|
||||
1. Add the following two methods to the `public` section of the `Mic` class:
|
||||
|
||||
```cpp
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
```
|
||||
|
||||
The `init` method contain code to initialize the `Mic` class. This method sets the correct voltage for the Mic pin, sets up the flash memory writer, writes the WAV file header, and configures the DMAC. The `reset` method resets the flash memory and re-writes the header after the audio has been captured and used.
|
||||
|
||||
### Task - capture audio
|
||||
|
||||
1. In the `main.cpp` file, and an include directive for the `mic.h` header file:
|
||||
|
||||
```cpp
|
||||
#include "mic.h"
|
||||
```
|
||||
|
||||
1. In the `setup` function, initialize the C button. Audio capture will start when this button is pressed, and continue for 4 seconds:
|
||||
|
||||
```cpp
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
```
|
||||
|
||||
1. Below this, initialize the microphone, then print to the console that audio is ready to be captured:
|
||||
|
||||
```cpp
|
||||
mic.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
```
|
||||
|
||||
1. Above the `loop` function, define a function to process the captured audio. For now this does nothing, but later in this lesson it will send the speech to be converted to text:
|
||||
|
||||
```cpp
|
||||
void processAudio()
|
||||
{
|
||||
|
||||
}
|
||||
```
|
||||
|
||||
1. Add the following to the `loop` function:
|
||||
|
||||
```cpp
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This code checks hte C button, and if this is pressed and recording hasn't started, then the `_isRecording` field of the `Mic` class is set to true. This will cause the `audioCallback` method of the `Mic` class to store audio until 4 seconds has been captured. Once 4 seconds of audio has been captured, the `_isRecording` field is set to false, and the `_isRecordingReady` field is set to true. This is then checked in the `loop` function, and when true the `processAudio` function is called, then the mic class is reset.
|
||||
|
||||
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Press the C button (the one on the left-hand side, closest to the power switch), and speak. 4 seconds of audio will be captured.
|
||||
|
||||
```output
|
||||
--- Available filters and text transformations: colorize, debug, default, direct, hexlify, log2file, nocontrol, printable, send_on_enter, time
|
||||
--- More details at http://bit.ly/pio-monitor-filters
|
||||
--- Miniterm on /dev/cu.usbmodem1101 9600,8,N,1 ---
|
||||
--- Quit: Ctrl+C | Menu: Ctrl+T | Help: Ctrl+T followed by Ctrl+H ---
|
||||
Ready.
|
||||
Starting recording...
|
||||
Finished recording
|
||||
```
|
||||
|
||||
> 💁 You can find this code in the [code-record/wio-terminal](code-record/wio-terminal) folder.
|
||||
|
||||
😀 Your audio recording program was a success!
|
||||
|
||||
@ -1,3 +1,11 @@
|
||||
# Configure your microphone and speakers - Wio Terminal
|
||||
|
||||
Coming soon!
|
||||
In this part of the lesson, you will add and speakers to your Wio Terminal. The Wio Terminal already has a microphone built-in, and this can be used to capture speech.
|
||||
|
||||
## Hardware
|
||||
|
||||
Coming soon
|
||||
|
||||
### Task - connect speakers
|
||||
|
||||
Coming soon
|
||||
|
||||
@ -1,3 +1,521 @@
|
||||
# Speech to text - Wio Terminal
|
||||
|
||||
Coming soon!
|
||||
In this part of the lesson, you will write code to convert speech in the captured audio to text using the speech service.
|
||||
|
||||
## Send the audio to the speech service
|
||||
|
||||
The audio can be sent to the speech service using the REST API. To use the speech service, first you need to request an access token, then use that token to access the REST API. These access tokens expire after 10 minutes, so your code should request them on a regular basis to ensure they are always up to date.
|
||||
|
||||
### Task - get an access token
|
||||
|
||||
1. Open the `smart-timer` project if it's not already open.
|
||||
|
||||
1. Add the following library dependencies to the `platformio.ini` file to access WiFi and handle JSON:
|
||||
|
||||
```ini
|
||||
seeed-studio/Seeed Arduino rpcWiFi @ 1.0.5
|
||||
seeed-studio/Seeed Arduino rpcUnified @ 2.1.3
|
||||
seeed-studio/Seeed_Arduino_mbedtls @ 3.0.1
|
||||
seeed-studio/Seeed Arduino RTC @ 2.0.0
|
||||
bblanchon/ArduinoJson @ 6.17.3
|
||||
```
|
||||
|
||||
1. Add the following code to the `config.h` header file:
|
||||
|
||||
```cpp
|
||||
const char *SSID = "<SSID>";
|
||||
const char *PASSWORD = "<PASSWORD>";
|
||||
|
||||
const char *SPEECH_API_KEY = "<API_KEY>";
|
||||
const char *SPEECH_LOCATION = "<LOCATION>";
|
||||
const char *LANGUAGE = "<LANGUAGE>";
|
||||
|
||||
const char *TOKEN_URL = "https://%s.api.cognitive.microsoft.com/sts/v1.0/issuetoken";
|
||||
```
|
||||
|
||||
Replace `<SSID>` and `<PASSWORD>` with the relevant values for your WiFi.
|
||||
|
||||
Replace `<API_KEY>` with the API key for your speech service resource. Replace `<LOCATION>` with the location you used when you created the speech service resource.
|
||||
|
||||
Replace `<LANGUAGE>` with the locale name for language you will be speaking in, for example `en-GB` for English, or `zn-HK` for Cantonese. You can find a list of the supported languages and their locale names in the [Language and voice support documentation on Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/language-support?WT.mc_id=academic-17441-jabenn#speech-to-text).
|
||||
|
||||
The `TOKEN_URL` constant is the URL of the token issuer without the location. This will be combined with the location later to get the full URL.
|
||||
|
||||
1. Just like connecting to Custom Vision, you will need to use an HTTPS connection to connect to the token issuing service. To the end of `config.h`, add the following code:
|
||||
|
||||
```cpp
|
||||
const char *TOKEN_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQAueRcfuAIek/4tmDg0xQwDANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwNjCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBALVGARl56bx3KBUSGuPc4H5uoNFkFH4e7pvTCxRi4j/+z+Xb\r\n"
|
||||
"wjEz+5CipDOqjx9/jWjskL5dk7PaQkzItidsAAnDCW1leZBOIi68Lff1bjTeZgMY\r\n"
|
||||
"iwdRd3Y39b/lcGpiuP2d23W95YHkMMT8IlWosYIX0f4kYb62rphyfnAjYb/4Od99\r\n"
|
||||
"ThnhlAxGtfvSbXcBVIKCYfZgqRvV+5lReUnd1aNjRYVzPOoifgSx2fRyy1+pO1Uz\r\n"
|
||||
"aMMNnIOE71bVYW0A1hr19w7kOb0KkJXoALTDDj1ukUEDqQuBfBxReL5mXiu1O7WG\r\n"
|
||||
"0vltg0VZ/SZzctBsdBlx1BkmWYBW261KZgBivrql5ELTKKd8qgtHcLQA5fl6JB0Q\r\n"
|
||||
"gs5XDaWehN86Gps5JW8ArjGtjcWAIP+X8CQaWfaCnuRm6Bk/03PQWhgdi84qwA0s\r\n"
|
||||
"sRfFJwHUPTNSnE8EiGVk2frt0u8PG1pwSQsFuNJfcYIHEv1vOzP7uEOuDydsmCjh\r\n"
|
||||
"lxuoK2n5/2aVR3BMTu+p4+gl8alXoBycyLmj3J/PUgqD8SL5fTCUegGsdia/Sa60\r\n"
|
||||
"N2oV7vQ17wjMN+LXa2rjj/b4ZlZgXVojDmAjDwIRdDUujQu0RVsJqFLMzSIHpp2C\r\n"
|
||||
"Zp7mIoLrySay2YYBu7SiNwL95X6He2kS8eefBBHjzwW/9FxGqry57i71c2cDAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQU1cFnOsKjnfR3UltZEjgp5lVou6UwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQB2oWc93fB8esci/8esixj++N22meiGDjgF\r\n"
|
||||
"+rA2LUK5IOQOgcUSTGKSqF9lYfAxPjrqPjDCUPHCURv+26ad5P/BYtXtbmtxJWu+\r\n"
|
||||
"cS5BhMDPPeG3oPZwXRHBJFAkY4O4AF7RIAAUW6EzDflUoDHKv83zOiPfYGcpHc9s\r\n"
|
||||
"kxAInCedk7QSgXvMARjjOqdakor21DTmNIUotxo8kHv5hwRlGhBJwps6fEVi1Bt0\r\n"
|
||||
"trpM/3wYxlr473WSPUFZPgP1j519kLpWOJ8z09wxay+Br29irPcBYv0GMXlHqThy\r\n"
|
||||
"8y4m/HyTQeI2IMvMrQnwqPpY+rLIXyviI2vLoI+4xKE4Rn38ZZ8m\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
```
|
||||
|
||||
This is the same certificate you used when connecting to Custom Vision.
|
||||
|
||||
1. Add an include for the WiFi header file and the config header file to the top of the `main.cpp` file:
|
||||
|
||||
```cpp
|
||||
#include <rpcWiFi.h>
|
||||
|
||||
#include "config.h"
|
||||
```
|
||||
|
||||
1. Add code to connect to WiFi in `main.cpp` above the `setup` function:
|
||||
|
||||
```cpp
|
||||
void connectWiFi()
|
||||
{
|
||||
while (WiFi.status() != WL_CONNECTED)
|
||||
{
|
||||
Serial.println("Connecting to WiFi..");
|
||||
WiFi.begin(SSID, PASSWORD);
|
||||
delay(500);
|
||||
}
|
||||
|
||||
Serial.println("Connected!");
|
||||
}
|
||||
```
|
||||
|
||||
1. Call this function from the `setup` function after the serial connection has been established:
|
||||
|
||||
```cpp
|
||||
connectWiFi();
|
||||
```
|
||||
|
||||
1. Create a new header file in the `src` folder called `speech_to_text.h`. In this header file, add the following code:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "mic.h"
|
||||
|
||||
class SpeechToText
|
||||
{
|
||||
public:
|
||||
|
||||
private:
|
||||
|
||||
};
|
||||
|
||||
SpeechToText speechToText;
|
||||
```
|
||||
|
||||
This includes some necessary header files for an HTTP connection, configuration and the `mic.h` header file, and defines a class called `SpeechToText`, before declaring an instance of that class that can be used later.
|
||||
|
||||
1. Add the following 2 fields to the `private` section of this class:
|
||||
|
||||
```cpp
|
||||
WiFiClientSecure _token_client;
|
||||
String _access_token;
|
||||
```
|
||||
|
||||
The `_token_client` is a WiFi Client that uses HTTPS and will be used to get the access token. This token will then be stored in `_access_token`.
|
||||
|
||||
1. Add the following method to the `private` section:
|
||||
|
||||
```cpp
|
||||
String getAccessToken()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, TOKEN_URL, SPEECH_LOCATION);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_token_client, url);
|
||||
|
||||
httpClient.addHeader("Ocp-Apim-Subscription-Key", SPEECH_API_KEY);
|
||||
int httpResultCode = httpClient.POST("{}");
|
||||
|
||||
if (httpResultCode != 200)
|
||||
{
|
||||
Serial.println("Error getting access token, trying again...");
|
||||
delay(10000);
|
||||
return getAccessToken();
|
||||
}
|
||||
|
||||
Serial.println("Got access token.");
|
||||
String result = httpClient.getString();
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return result;
|
||||
}
|
||||
```
|
||||
|
||||
This code builds the URL for the token issuer API using the location of the speech resource. It then creates an `HTTPClient` to make the web request, setting it up to use the WiFi client configured with the token endpoints certificate. It sets the API key as a header for the call. It then makes a POST request to get the certificate, retrying if it gets any errors. Finally the access token is returned.
|
||||
|
||||
1. To the `public` section, add an `init` method that sets up the token client:
|
||||
|
||||
```cpp
|
||||
void init()
|
||||
{
|
||||
_token_client.setCACert(TOKEN_CERTIFICATE);
|
||||
_access_token = getAccessToken();
|
||||
}
|
||||
```
|
||||
|
||||
This sets the certificate on the WiFi client, then gets the access token.
|
||||
|
||||
1. In `main.cpp`, add this new header file to the include directives:
|
||||
|
||||
```cpp
|
||||
#include "speech_to_text.h"
|
||||
```
|
||||
|
||||
1. Initialize the `SpeechToText` class at the end of the `setup` function, after the `mic.init` call but before `Ready` is written to the serial monitor:
|
||||
|
||||
```cpp
|
||||
speechToText.init();
|
||||
```
|
||||
|
||||
### Task - read audio from flash memory
|
||||
|
||||
1. In an earlier part of this lesson, the audio was recorded to the flash memory. This audio will need to be sent to the Speech Services REST API, so it needs to be read from the flash memory. It can't be loaded into an in-memory buffer as it would be too large. The `HTTPClient` class that makes REST calls can stream data using an Arduino Stream - a class that can load data in small chunks, sending the chunks one at a time as part of the request. Every time you call `read` on a stream it returns the next block of data. An Arduino stream can be created that can read from the flash memory. Create a new file called `flash_stream.h` in the `src` folder, and add the following code to it:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <sfud.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class FlashStream : public Stream
|
||||
{
|
||||
public:
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
}
|
||||
|
||||
virtual int available()
|
||||
{
|
||||
}
|
||||
|
||||
virtual int read()
|
||||
{
|
||||
}
|
||||
|
||||
virtual int peek()
|
||||
{
|
||||
}
|
||||
private:
|
||||
|
||||
};
|
||||
```
|
||||
|
||||
This declares the `FlashStream` class, deriving from the Arduino `Stream` class. This is an abstract class - derived classes have to implement a few methods before the class can be instantiated, and these methods are defined in this class.
|
||||
|
||||
✅ Read more on Arduino Streams in the [Arduino Stream documentation](https://www.arduino.cc/reference/en/language/functions/communication/stream/)
|
||||
|
||||
1. Add the following fields to the `private` section:
|
||||
|
||||
```cpp
|
||||
size_t _pos;
|
||||
size_t _flash_address;
|
||||
const sfud_flash *_flash;
|
||||
|
||||
byte _buffer[HTTP_TCP_BUFFER_SIZE];
|
||||
```
|
||||
|
||||
This defines a temporary buffer to store data read from the flash memory, along with fields to store the current position when reading from the buffer, the current address to read from the flash memory, and the flash memory device.
|
||||
|
||||
1. In the `private` section, add the following method:
|
||||
|
||||
```cpp
|
||||
void populateBuffer()
|
||||
{
|
||||
sfud_read(_flash, _flash_address, HTTP_TCP_BUFFER_SIZE, _buffer);
|
||||
_flash_address += HTTP_TCP_BUFFER_SIZE;
|
||||
_pos = 0;
|
||||
}
|
||||
```
|
||||
|
||||
This code reads from the flash memory at the current address and stores the data in a buffer. It then increments the address, so the next call reads the next block of memory. The buffer is sized based on the largest chunk that the `HTTPClient` will send to the REST API at one time.
|
||||
|
||||
> 💁 Erasing flash memory has to be done using the grain size, reading on the other hand does not.
|
||||
|
||||
1. In the `public` section of this class, add a constructor:
|
||||
|
||||
```cpp
|
||||
FlashStream()
|
||||
{
|
||||
_pos = 0;
|
||||
_flash_address = 0;
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
|
||||
populateBuffer();
|
||||
}
|
||||
```
|
||||
|
||||
This constructor sets up all the fields to start reading from the start of the flash memory block, and loads the first chunk of data into the buffer.
|
||||
|
||||
1. Implement the `write` method. This stream will only read data, so this can do nothing and return 0:
|
||||
|
||||
```cpp
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
```
|
||||
|
||||
1. Implement the `peek` method. This returns the data at the current position without moving the stream along. Calling `peek` multiple times will always return the same data as long as no data is read from the stream.
|
||||
|
||||
```cpp
|
||||
virtual int peek()
|
||||
{
|
||||
return _buffer[_pos];
|
||||
}
|
||||
```
|
||||
|
||||
1. Implement the `available` function. This returns how many bytes can be read from the stream, or -1 if the stream is complete. For this class, the maximum available will be no more than the HTTPClient's chunk size. When this stream is used in the HTTP client it calls this function to see how much data is available, then requests that much data to send to the REST API. We don't want each chunk to be more than the HTTP clients chunk size, so if more than that is available, the chunk size is returned. If less, then what is available is returned. Once all the data has been streamed, -1 is returned.
|
||||
|
||||
```cpp
|
||||
virtual int available()
|
||||
{
|
||||
int remaining = BUFFER_SIZE - ((_flash_address - HTTP_TCP_BUFFER_SIZE) + _pos);
|
||||
int bytes_available = min(HTTP_TCP_BUFFER_SIZE, remaining);
|
||||
|
||||
if (bytes_available == 0)
|
||||
{
|
||||
bytes_available = -1;
|
||||
}
|
||||
|
||||
return bytes_available;
|
||||
}
|
||||
```
|
||||
|
||||
1. Implement the `read` method to return the next byte from the buffer, incrementing the position. If the position exceeds the size of the buffer, it populates the buffer with the next block from the flash memory and resets the position.
|
||||
|
||||
```cpp
|
||||
virtual int read()
|
||||
{
|
||||
int retVal = _buffer[_pos++];
|
||||
|
||||
if (_pos == HTTP_TCP_BUFFER_SIZE)
|
||||
{
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
return retVal;
|
||||
}
|
||||
```
|
||||
|
||||
1. In the `speech_to_text.h` header file, add an include directive for this new header file:
|
||||
|
||||
```cpp
|
||||
#include "flash_stream.h"
|
||||
```
|
||||
|
||||
### Task - convert the speech to text
|
||||
|
||||
1. The speech can be converted to text by sending the audio to the Speech Service via a REST API. This REST API has a different certificate to the token issuer, so add the following code to the `config.h` header file to define this certificate:
|
||||
|
||||
```cpp
|
||||
const char *SPEECH_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQCq+mxcpjxFFB6jvh98dTFzANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwMTCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBAMedcDrkXufP7pxVm1FHLDNA9IjwHaMoaY8arqqZ4Gff4xyr\r\n"
|
||||
"RygnavXL7g12MPAx8Q6Dd9hfBzrfWxkF0Br2wIvlvkzW01naNVSkHp+OS3hL3W6n\r\n"
|
||||
"l/jYvZnVeJXjtsKYcXIf/6WtspcF5awlQ9LZJcjwaH7KoZuK+THpXCMtzD8XNVdm\r\n"
|
||||
"GW/JI0C/7U/E7evXn9XDio8SYkGSM63aLO5BtLCv092+1d4GGBSQYolRq+7Pd1kR\r\n"
|
||||
"EkWBPm0ywZ2Vb8GIS5DLrjelEkBnKCyy3B0yQud9dpVsiUeE7F5sY8Me96WVxQcb\r\n"
|
||||
"OyYdEY/j/9UpDlOG+vA+YgOvBhkKEjiqygVpP8EZoMMijephzg43b5Qi9r5UrvYo\r\n"
|
||||
"o19oR/8pf4HJNDPF0/FJwFVMW8PmCBLGstin3NE1+NeWTkGt0TzpHjgKyfaDP2tO\r\n"
|
||||
"4bCk1G7pP2kDFT7SYfc8xbgCkFQ2UCEXsaH/f5YmpLn4YPiNFCeeIida7xnfTvc4\r\n"
|
||||
"7IxyVccHHq1FzGygOqemrxEETKh8hvDR6eBdrBwmCHVgZrnAqnn93JtGyPLi6+cj\r\n"
|
||||
"WGVGtMZHwzVvX1HvSFG771sskcEjJxiQNQDQRWHEh3NxvNb7kFlAXnVdRkkvhjpR\r\n"
|
||||
"GchFhTAzqmwltdWhWDEyCMKC2x/mSZvZtlZGY+g37Y72qHzidwtyW7rBetZJAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQUDyBd16FXlduSzyvQx8J3BM5ygHYwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQAlFvNh7QgXVLAZSsNR2XRmIn9iS8OHFCBA\r\n"
|
||||
"WxKJoi8YYQafpMTkMqeuzoL3HWb1pYEipsDkhiMnrpfeYZEA7Lz7yqEEtfgHcEBs\r\n"
|
||||
"K9KcStQGGZRfmWU07hPXHnFz+5gTXqzCE2PBMlRgVUYJiA25mJPXfB00gDvGhtYa\r\n"
|
||||
"+mENwM9Bq1B9YYLyLjRtUz8cyGsdyTIG/bBM/Q9jcV8JGqMU/UjAdh1pFyTnnHEl\r\n"
|
||||
"Y59Npi7F87ZqYYJEHJM2LGD+le8VsHjgeWX2CJQko7klXvcizuZvUEDTjHaQcs2J\r\n"
|
||||
"+kPgfyMIOY1DMJ21NxOJ2xPRC/wAh/hzSBRVtoAnyuxtkZ4VjIOh\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
```
|
||||
|
||||
1. Add a constant to this file for the speech URL without the location. This will be combined with the location and language later to get the full URL.
|
||||
|
||||
```cpp
|
||||
const char *SPEECH_URL = "https://%s.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=%s";
|
||||
```
|
||||
|
||||
1. In the `speech_to_text.h` header file, in the `private` section of the `SpeechToText` class, define a field for a WiFi Client using the speech certificate:
|
||||
|
||||
```cpp
|
||||
WiFiClientSecure _speech_client;
|
||||
```
|
||||
|
||||
1. In the `init` method, set the certificate on this WiFi Client:
|
||||
|
||||
```cpp
|
||||
_speech_client.setCACert(SPEECH_CERTIFICATE);
|
||||
```
|
||||
|
||||
1. Add the following code to the `public` section of the `SpeechToText` class to define a method to convert speech to text:
|
||||
|
||||
```cpp
|
||||
String convertSpeechToText()
|
||||
{
|
||||
|
||||
}
|
||||
```
|
||||
|
||||
1. Add the following code to this method to create an HTTP client using the WiFi client configured with the speech certificate, and using the speech URL set with the location and language:
|
||||
|
||||
```cpp
|
||||
char url[128];
|
||||
sprintf(url, SPEECH_URL, SPEECH_LOCATION, LANGUAGE);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_speech_client, url);
|
||||
```
|
||||
|
||||
1. Some headers need to be set on the connection:
|
||||
|
||||
```cpp
|
||||
httpClient.addHeader("Authorization", String("Bearer ") + _access_token);
|
||||
httpClient.addHeader("Content-Type", String("audio/wav; codecs=audio/pcm; samplerate=") + String(RATE));
|
||||
httpClient.addHeader("Accept", "application/json;text/xml");
|
||||
```
|
||||
|
||||
This sets headers for the authorization using the access token, the audio format using the sample rate, and sets that the client expects the result as JSON.
|
||||
|
||||
1. After this, add the following code to make the REST API call:
|
||||
|
||||
```cpp
|
||||
Serial.println("Sending speech...");
|
||||
|
||||
FlashStream stream;
|
||||
int httpResponseCode = httpClient.sendRequest("POST", &stream, BUFFER_SIZE);
|
||||
|
||||
Serial.println("Speech sent!");
|
||||
```
|
||||
|
||||
This creates a `FlashStream` and uses it to stream data to the REST API.
|
||||
|
||||
1. Below this, add the following code:
|
||||
|
||||
```cpp
|
||||
String text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
text = obj["DisplayText"].as<String>();
|
||||
}
|
||||
else if (httpResponseCode == 401)
|
||||
{
|
||||
Serial.println("Access token expired, trying again with a new token");
|
||||
_access_token = getAccessToken();
|
||||
return convertSpeechToText();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to convert text to speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
```
|
||||
|
||||
This code checks the response code.
|
||||
|
||||
If it is 200, the code for success, then the result is retrieved, decoded from JSON, and the `DisplayText` property is set into the `text` variable. This is the property that the text version of the speech is returned in.
|
||||
|
||||
If the response code is 401, then the access token has expired (these tokens only last 10 minutes). A new access token is requested, and the call is made again.
|
||||
|
||||
Otherwise, an error is sent to the serial monitor, and the `text` is left blank.
|
||||
|
||||
1. Add the following code to the end of this method to close the HTTP client and return the text:
|
||||
|
||||
```cpp
|
||||
httpClient.end();
|
||||
|
||||
return text;
|
||||
```
|
||||
|
||||
1. In `main.cpp` call this new `convertSpeechToText` method in the `processAudio` function, then log out the speech to the serial monitor:
|
||||
|
||||
```cpp
|
||||
String text = speechToText.convertSpeechToText();
|
||||
Serial.println(text);
|
||||
```
|
||||
|
||||
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Press the C button (the one on the left-hand side, closest to the power switch), and speak. 4 seconds of audio will be captured, then converted to text.
|
||||
|
||||
```output
|
||||
--- Available filters and text transformations: colorize, debug, default, direct, hexlify, log2file, nocontrol, printable, send_on_enter, time
|
||||
--- More details at http://bit.ly/pio-monitor-filters
|
||||
--- Miniterm on /dev/cu.usbmodem1101 9600,8,N,1 ---
|
||||
--- Quit: Ctrl+C | Menu: Ctrl+T | Help: Ctrl+T followed by Ctrl+H ---
|
||||
Connecting to WiFi..
|
||||
Connected!
|
||||
Got access token.
|
||||
Ready.
|
||||
Starting recording...
|
||||
Finished recording
|
||||
Sending speech...
|
||||
Speech sent!
|
||||
{"RecognitionStatus":"Success","DisplayText":"Set a 2 minute and 27 second timer.","Offset":4700000,"Duration":35300000}
|
||||
Set a 2 minute and 27 second timer.
|
||||
```
|
||||
|
||||
> 💁 You can find this code in the [code-speech-to-text/wio-terminal](code-speech-to-text/wio-terminal) folder.
|
||||
|
||||
😀 Your speech to text program was a success!
|
||||
|
||||
@ -1,43 +0,0 @@
|
||||
from typing import List
|
||||
import logging
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
import json
|
||||
import os
|
||||
from azure.cognitiveservices.language.luis.runtime import LUISRuntimeClient
|
||||
from msrest.authentication import CognitiveServicesCredentials
|
||||
|
||||
def main(events: List[func.EventHubEvent]):
|
||||
luis_key = os.environ['LUIS_KEY']
|
||||
endpoint_url = os.environ['LUIS_ENDPOINT_URL']
|
||||
app_id = os.environ['LUIS_APP_ID']
|
||||
|
||||
credentials = CognitiveServicesCredentials(luis_key)
|
||||
client = LUISRuntimeClient(endpoint=endpoint_url, credentials=credentials)
|
||||
|
||||
for event in events:
|
||||
logging.info('Python EventHub trigger processed an event: %s',
|
||||
event.get_body().decode('utf-8'))
|
||||
|
||||
event_body = json.loads(event.get_body().decode('utf-8'))
|
||||
prediction_request = { 'query' : event_body['speech'] }
|
||||
|
||||
prediction_response = client.prediction.get_slot_prediction(app_id, 'Staging', prediction_request)
|
||||
|
||||
if prediction_response.prediction.top_intent == 'set timer':
|
||||
numbers = prediction_response.prediction.entities['number']
|
||||
time_units = prediction_response.prediction.entities['time unit']
|
||||
total_seconds = 0
|
||||
|
||||
for i in range(0, len(numbers)):
|
||||
number = numbers[i]
|
||||
time_unit = time_units[i][0]
|
||||
|
||||
if time_unit == 'minute':
|
||||
total_seconds += number * 60
|
||||
else:
|
||||
total_seconds += number
|
||||
|
||||
logging.info(f'Timer required for {total_seconds} seconds')
|
||||
|
||||
@ -1,15 +0,0 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"type": "eventHubTrigger",
|
||||
"name": "events",
|
||||
"direction": "in",
|
||||
"eventHubName": "samples-workitems",
|
||||
"connection": "IOT_HUB_CONNECTION_STRING",
|
||||
"cardinality": "many",
|
||||
"consumerGroup": "$Default",
|
||||
"dataType": "binary"
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -0,0 +1,44 @@
|
||||
import logging
|
||||
|
||||
import azure.functions as func
|
||||
import json
|
||||
import os
|
||||
from azure.cognitiveservices.language.luis.runtime import LUISRuntimeClient
|
||||
from msrest.authentication import CognitiveServicesCredentials
|
||||
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
luis_key = os.environ['LUIS_KEY']
|
||||
endpoint_url = os.environ['LUIS_ENDPOINT_URL']
|
||||
app_id = os.environ['LUIS_APP_ID']
|
||||
|
||||
credentials = CognitiveServicesCredentials(luis_key)
|
||||
client = LUISRuntimeClient(endpoint=endpoint_url, credentials=credentials)
|
||||
|
||||
text = req.params.get('text')
|
||||
prediction_request = { 'query' : text }
|
||||
|
||||
prediction_response = client.prediction.get_slot_prediction(app_id, 'Staging', prediction_request)
|
||||
|
||||
if prediction_response.prediction.top_intent == 'set timer':
|
||||
numbers = prediction_response.prediction.entities['number']
|
||||
time_units = prediction_response.prediction.entities['time unit']
|
||||
total_seconds = 0
|
||||
|
||||
for i in range(0, len(numbers)):
|
||||
number = numbers[i]
|
||||
time_unit = time_units[i][0]
|
||||
|
||||
if time_unit == 'minute':
|
||||
total_seconds += number * 60
|
||||
else:
|
||||
total_seconds += number
|
||||
|
||||
logging.info(f'Timer required for {total_seconds} seconds')
|
||||
|
||||
payload = {
|
||||
'seconds': total_seconds
|
||||
}
|
||||
return func.HttpResponse(json.dumps(payload), status_code=200)
|
||||
|
||||
return func.HttpResponse(status_code=404)
|
||||
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -1,15 +0,0 @@
|
||||
{
|
||||
"version": "2.0",
|
||||
"logging": {
|
||||
"applicationInsights": {
|
||||
"samplingSettings": {
|
||||
"isEnabled": true,
|
||||
"excludedTypes": "Request"
|
||||
}
|
||||
}
|
||||
},
|
||||
"extensionBundle": {
|
||||
"id": "Microsoft.Azure.Functions.ExtensionBundle",
|
||||
"version": "[2.*, 3.0.0)"
|
||||
}
|
||||
}
|
||||
@ -1,12 +0,0 @@
|
||||
{
|
||||
"IsEncrypted": false,
|
||||
"Values": {
|
||||
"FUNCTIONS_WORKER_RUNTIME": "python",
|
||||
"AzureWebJobsStorage": "UseDevelopmentStorage=true",
|
||||
"IOT_HUB_CONNECTION_STRING": "<connection string>",
|
||||
"LUIS_KEY": "<primary key>",
|
||||
"LUIS_ENDPOINT_URL": "<endpoint url>",
|
||||
"LUIS_APP_ID": "<app id>",
|
||||
"REGISTRY_MANAGER_CONNECTION_STRING": "<connection string>"
|
||||
}
|
||||
}
|
||||
@ -1,4 +0,0 @@
|
||||
# Do not include azure-functions-worker as it may conflict with the Azure Functions platform
|
||||
|
||||
azure-functions
|
||||
azure-cognitiveservices-language-luis
|
||||
@ -1,60 +0,0 @@
|
||||
from typing import List
|
||||
import logging
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
import json
|
||||
import os
|
||||
from azure.cognitiveservices.language.luis.runtime import LUISRuntimeClient
|
||||
from msrest.authentication import CognitiveServicesCredentials
|
||||
|
||||
from azure.iot.hub import IoTHubRegistryManager
|
||||
from azure.iot.hub.models import CloudToDeviceMethod
|
||||
|
||||
def main(events: List[func.EventHubEvent]):
|
||||
luis_key = os.environ['LUIS_KEY']
|
||||
endpoint_url = os.environ['LUIS_ENDPOINT_URL']
|
||||
app_id = os.environ['LUIS_APP_ID']
|
||||
registry_manager_connection_string = os.environ['REGISTRY_MANAGER_CONNECTION_STRING']
|
||||
|
||||
credentials = CognitiveServicesCredentials(luis_key)
|
||||
client = LUISRuntimeClient(endpoint=endpoint_url, credentials=credentials)
|
||||
|
||||
for event in events:
|
||||
logging.info('Python EventHub trigger processed an event: %s',
|
||||
event.get_body().decode('utf-8'))
|
||||
|
||||
device_id = event.iothub_metadata['connection-device-id']
|
||||
|
||||
event_body = json.loads(event.get_body().decode('utf-8'))
|
||||
prediction_request = { 'query' : event_body['speech'] }
|
||||
|
||||
prediction_response = client.prediction.get_slot_prediction(app_id, 'Staging', prediction_request)
|
||||
|
||||
if prediction_response.prediction.top_intent == 'set timer':
|
||||
numbers = prediction_response.prediction.entities['number']
|
||||
time_units = prediction_response.prediction.entities['time unit']
|
||||
total_seconds = 0
|
||||
|
||||
for i in range(0, len(numbers)):
|
||||
number = numbers[i]
|
||||
time_unit = time_units[i][0]
|
||||
|
||||
if time_unit == 'minute':
|
||||
total_seconds += number * 60
|
||||
else:
|
||||
total_seconds += number
|
||||
|
||||
logging.info(f'Timer required for {total_seconds} seconds')
|
||||
|
||||
payload = {
|
||||
'seconds': total_seconds
|
||||
}
|
||||
direct_method = CloudToDeviceMethod(method_name='set-timer', payload=json.dumps(payload))
|
||||
|
||||
registry_manager_connection_string = os.environ['REGISTRY_MANAGER_CONNECTION_STRING']
|
||||
registry_manager = IoTHubRegistryManager(registry_manager_connection_string)
|
||||
|
||||
registry_manager.invoke_device_method(device_id, direct_method)
|
||||
|
||||
|
||||
@ -1,15 +0,0 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"type": "eventHubTrigger",
|
||||
"name": "events",
|
||||
"direction": "in",
|
||||
"eventHubName": "samples-workitems",
|
||||
"connection": "IOT_HUB_CONNECTION_STRING",
|
||||
"cardinality": "many",
|
||||
"consumerGroup": "$Default",
|
||||
"dataType": "binary"
|
||||
}
|
||||
]
|
||||
}
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
Loading…
Reference in new issue