msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

fix cors, test=doc

Browse Source
pull/1898/head
lym0302 3 years ago
parent 8ed8c9c161
commit c5d2224d6d
20 changed files with 193 additions and 109 deletions
Show Stats Download Patch File Download Diff File

30
demos/speech_server/README.md
Unescape View File

@ -52,8 +52,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete.
[2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
```
@ -75,8 +75,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete.
[2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
```
@ -84,6 +84,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
### 4. ASR Client Usage
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
@ -132,6 +135,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
### 5. TTS Client Usage
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
If `127.0.0.1` is not accessible, you need to use the actual service IP address
```bash
paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```
@ -192,6 +198,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
### 6. CLS Client Usage
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
@ -242,9 +251,11 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
``` bash
paddlespeech_client vector --task spk --server_ip 127.0.0.1 --port 8090 --input 85236145389.wav
```
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
``` bash
paddlespeech_client vector --task spk --server_ip 127.0.0.1 --port 8090 --input 85236145389.wav
```
* Usage:
@ -297,6 +308,8 @@ print(res)
- Command Line (Recommended)
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
``` bash
paddlespeech_client vector --task score --server_ip 127.0.0.1 --port 8090 --enroll 85236145389.wav --test 123456789.wav
```
@ -357,6 +370,9 @@ print(res)
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
``` bash
paddlespeech_client text --server_ip 127.0.0.1 --port 8090 --input "我认为跑步最重要的就是给我带来了身体健康"
```

153
demos/speech_server/README_cn.md
Unescape View File

@ -53,8 +53,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete.
[2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
```
@ -76,39 +76,42 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete.
[2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit)
```
### 4. ASR 客户端使用方法
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
```
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
使用帮助:
```bash
paddlespeech_client asr --help
```
```
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
参数:
- `server_ip`: 服务端ip地址，默认: 127.0.0.1。
- `port`: 服务端口，默认: 8090。
- `input`(必须输入): 用于识别的音频文件。
- `sample_rate`: 音频采样率，默认值：16000。
- `lang`: 模型语言，默认值：zh_cn。
- `audio_format`: 音频格式，默认值：wav。
```
输出:
使用帮助:
```bash
paddlespeech_client asr --help
```
参数:
- `server_ip`: 服务端ip地址，默认: 127.0.0.1。
- `port`: 服务端口，默认: 8090。
- `input`(必须输入): 用于识别的音频文件。
- `sample_rate`: 音频采样率，默认值：16000。
- `lang`: 模型语言，默认值：zh_cn。
- `audio_format`: 音频格式，默认值：wav。
输出:
```bash
[2022-02-23 18:11:22,819] [ INFO] - {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'transcription': '我认为跑步最重要的就是给我带来了身体健康'}}
[2022-02-23 18:11:22,820] [ INFO] - time cost 0.689145 s.
```
```bash
[2022-02-23 18:11:22,819] [ INFO] - {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'transcription': '我认为跑步最重要的就是给我带来了身体健康'}}
[2022-02-23 18:11:22,820] [ INFO] - time cost 0.689145 s.
```
- Python API
```python
@ -135,33 +138,35 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
### 5. TTS 客户端使用方法
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
```bash
paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```
使用帮助:
```bash
paddlespeech_client tts --help
```
参数:
- `server_ip`: 服务端ip地址，默认: 127.0.0.1。
- `port`: 服务端口，默认: 8090。
- `input`(必须输入): 待合成的文本。
- `spk_id`: 说话人 id，用于多说话人语音合成，默认值： 0。
- `speed`: 音频速度，该值应设置在 0 到 3 之间。 默认值：1.0
- `volume`: 音频音量，该值应设置在 0 到 3 之间。 默认值： 1.0
- `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认与模型相同。 默认值：0
- `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。
输出:
```bash
[2022-02-23 15:20:37,875] [ INFO] - {'description': 'success.'}
[2022-02-23 15:20:37,875] [ INFO] - Save synthesized audio successfully on output.wav.
[2022-02-23 15:20:37,875] [ INFO] - Audio duration: 3.612500 s.
[2022-02-23 15:20:37,875] [ INFO] - Response time: 0.348050 s.
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```bash
paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```
使用帮助:
```bash
paddlespeech_client tts --help
```
参数:
- `server_ip`: 服务端ip地址，默认: 127.0.0.1。
- `port`: 服务端口，默认: 8090。
- `input`(必须输入): 待合成的文本。
- `spk_id`: 说话人 id，用于多说话人语音合成，默认值： 0。
- `speed`: 音频速度，该值应设置在 0 到 3 之间。 默认值：1.0
- `volume`: 音频音量，该值应设置在 0 到 3 之间。 默认值： 1.0
- `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认与模型相同。 默认值：0
- `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。
输出:
```bash
[2022-02-23 15:20:37,875] [ INFO] - {'description': 'success.'}
[2022-02-23 15:20:37,875] [ INFO] - Save synthesized audio successfully on output.wav.
[2022-02-23 15:20:37,875] [ INFO] - Audio duration: 3.612500 s.
[2022-02-23 15:20:37,875] [ INFO] - Response time: 0.348050 s.
```
- Python API
```python
@ -197,9 +202,12 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
```
paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```
paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
使用帮助:
@ -247,15 +255,17 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
注意： 初次使用客户端时响应时间会略长
* 命令行 (推荐使用)
``` bash
paddlespeech_client vector --task spk --server_ip 127.0.0.1 --port 8090 --input 85236145389.wav
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
``` bash
paddlespeech_client vector --task spk --server_ip 127.0.0.1 --port 8090 --input 85236145389.wav
```
* 使用帮助:
``` bash
paddlespeech_client vector --help
```
``` bash
paddlespeech_client vector --help
```
* 参数:
* server_ip: 服务端ip地址，默认: 127.0.0.1。
* port: 服务端口，默认: 8090。
@ -299,15 +309,17 @@ print(res)
注意： 初次使用客户端时响应时间会略长
* 命令行 (推荐使用)
``` bash
paddlespeech_client vector --task score --server_ip 127.0.0.1 --port 8090 --enroll 85236145389.wav --test 123456789.wav
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
``` bash
paddlespeech_client vector --task score --server_ip 127.0.0.1 --port 8090 --enroll 85236145389.wav --test 123456789.wav
```
* 使用帮助:
``` bash
paddlespeech_client vector --help
```
``` bash
paddlespeech_client vector --help
```
* 参数:
* server_ip: 服务端ip地址，默认: 127.0.0.1。
@ -357,9 +369,12 @@ print(res)
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
``` bash
paddlespeech_client text --server_ip 127.0.0.1 --port 8090 --input "我认为跑步最重要的就是给我带来了身体健康"
```
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
``` bash
paddlespeech_client text --server_ip 127.0.0.1 --port 8090 --input "我认为跑步最重要的就是给我带来了身体健康"
```
使用帮助:
@ -409,4 +424,4 @@ print(res)
通过 `paddlespeech_server stats --task vector` 获取Vector服务支持的所有模型。
### Text支持的模型
通过 `paddlespeech_server stats --task text` 获取Text服务支持的所有模型。
通过 `paddlespeech_server stats --task text` 获取Text服务支持的所有模型。

2
demos/speech_server/asr_client.sh
Unescape View File

@ -1,4 +1,6 @@
#!/bin/bash
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav

2
demos/speech_server/cls_client.sh
Unescape View File

@ -1,4 +1,6 @@
#!/bin/bash
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav --topk 1

4
demos/speech_server/conf/application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8090
# The task format in the engin_list is: <speech task>_<engine type>
@ -157,4 +157,4 @@ vector_python:
sample_rate: 16000
cfg_path: # [optional]
ckpt_path: # [optional]
device: # set 'gpu:id' or 'cpu'
device: # set 'gpu:id' or 'cpu'

1
demos/speech_server/tts_client.sh
Unescape View File

@ -1,3 +1,4 @@
#!/bin/bash
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav

26
demos/streaming_asr_server/README.md
Unescape View File

@ -119,9 +119,12 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
**Note:** The response time will be slightly longer when using the client for the first time
- Command Line (Recommended)
```
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
Usage:
@ -374,10 +377,13 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
### 2. Client usage
**Note** The response time will be slightly longer when using the client for the first time
- Command line
```
paddlespeech_client text --server_ip 127.0.0.1 --port 8190 --input "我认为跑步最重要的就是给我带来了身体健康"
```
- Command line:
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
paddlespeech_client text --server_ip 127.0.0.1 --port 8190 --input "我认为跑步最重要的就是给我带来了身体健康"
```
Output
```
@ -419,6 +425,9 @@ bash server.sh
### 2. Call client
- Command line
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav
```
@ -494,6 +503,9 @@ bash server.sh
```
- Use script
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```
python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav
```

12
demos/streaming_asr_server/README_cn.md
Unescape View File

@ -125,6 +125,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wav
```
@ -384,6 +387,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
**注意：** 初次使用客户端时响应时间会略长
- 命令行 (推荐使用)
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```
paddlespeech_client text --server_ip 127.0.0.1 --port 8190 --input "我认为跑步最重要的就是给我带来了身体健康"
```
@ -427,6 +433,9 @@ bash server.sh
### 2. 调用服务
- 使用命令行：
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav
```
@ -502,6 +511,9 @@ bash server.sh
```
- 使用脚本调用
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```
python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav
```

2
demos/streaming_asr_server/test.sh
Unescape View File

@ -2,9 +2,11 @@
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav
# read the wav and pass it to only streaming asr service
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
# python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --wavfile ./zh.wav
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --input ./zh.wav
# read the wav and call streaming and punc service
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
# python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav
paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav

20
demos/streaming_tts_server/README.md
Unescape View File

@ -63,8 +63,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
[2022-04-24 20:05:28] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-24 20:05:28] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-24 20:05:28] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-24 20:05:28] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -90,8 +90,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
[2022-04-24 21:00:17] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-24 21:00:17] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-24 21:00:17] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-24 21:00:17] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -101,6 +101,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
Access http streaming TTS service:
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```bash
paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```
@ -198,8 +200,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
[2022-04-27 10:18:09] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-27 10:18:09] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-27 10:18:09] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:18:09] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -226,8 +228,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
[2022-04-27 10:20:16] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-27 10:20:16] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-27 10:20:16] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:20:16] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -236,6 +238,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
Access websocket streaming TTS service:
If `127.0.0.1` is not accessible, you need to use the actual service IP address.
```bash
paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```

20
demos/streaming_tts_server/README_cn.md
Unescape View File

@ -62,8 +62,8 @@
[2022-04-24 20:05:28] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-24 20:05:28] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-24 20:05:28] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-24 20:05:28] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -89,8 +89,8 @@
[2022-04-24 21:00:17] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-24 21:00:17] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-24 21:00:17] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-24 21:00:17] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -100,6 +100,8 @@
访问 http 流式TTS服务：
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```bash
paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```
@ -198,8 +200,8 @@
[2022-04-27 10:18:09] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-27 10:18:09] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-27 10:18:09] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:18:09] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -226,8 +228,8 @@
[2022-04-27 10:20:16] [INFO] [on.py:45] Waiting for application startup.
INFO: Application startup complete.
[2022-04-27 10:20:16] [INFO] [on.py:59] Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
[2022-04-27 10:20:16] [INFO] [server.py:211] Uvicorn running on http://127.0.0.1:8092 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
[2022-04-27 10:20:16] [INFO] [server.py:211] Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
```
@ -236,6 +238,8 @@
访问 websocket 流式TTS服务：
若 `127.0.0.1` 不能访问，则需要使用实际服务 IP 地址
```bash
paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
```

2
demos/streaming_tts_server/conf/tts_online_application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8092
# The task format in the engin_list is: <speech task>_<engine type>

4
demos/streaming_tts_server/test_client.sh
Unescape View File

@ -1,7 +1,9 @@
#!/bin/bash
# http client test
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
# websocket client test
#paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
# If `127.0.0.1` is not accessible, you need to use the actual service IP address.
# paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol websocket --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav

2
paddlespeech/server/bin/paddlespeech_client.py
Unescape View File

@ -20,6 +20,7 @@ import os
import random
import sys
import time
import warnings
from typing import List
import numpy as np
@ -34,6 +35,7 @@ from paddlespeech.server.utils.audio_handler import ASRWsAudioHandler
from paddlespeech.server.utils.audio_process import wav2pcm
from paddlespeech.server.utils.util import compute_delay
from paddlespeech.server.utils.util import wav2base64
warnings.filterwarnings("ignore")
__all__ = [
'TTSClientExecutor', 'TTSOnlineClientExecutor', 'ASRClientExecutor',

10
paddlespeech/server/bin/paddlespeech_server.py
Unescape View File

@ -13,11 +13,13 @@
# limitations under the License.
import argparse
import sys
import warnings
from typing import List
import uvicorn
from fastapi import FastAPI
from prettytable import PrettyTable
from starlette.middleware.cors import CORSMiddleware
from ..executor import BaseExecutor
from ..util import cli_server_register
@ -27,12 +29,20 @@ from paddlespeech.server.engine.engine_pool import init_engine_pool
from paddlespeech.server.restful.api import setup_router as setup_http_router
from paddlespeech.server.utils.config import get_config
from paddlespeech.server.ws.api import setup_router as setup_ws_router
warnings.filterwarnings("ignore")
__all__ = ['ServerExecutor', 'ServerStatsExecutor']
app = FastAPI(
title="PaddleSpeech Serving API", description="Api", version="0.0.1")
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"])
@cli_server_register(
name='paddlespeech_server.start', description='Start the service')

4
paddlespeech/server/conf/application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8090
# The task format in the engin_list is: <speech task>_<engine type>
@ -157,4 +157,4 @@ vector_python:
sample_rate: 16000
cfg_path: # [optional]
ckpt_path: # [optional]
device: # set 'gpu:id' or 'cpu'
device: # set 'gpu:id' or 'cpu'

2
paddlespeech/server/conf/tts_online_application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8092
# The task format in the engin_list is: <speech task>_<engine type>

2
tests/unit/server/offline/conf/application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8090
# The task format in the engin_list is: <speech task>_<engine type>

2
tests/unit/server/online/tts/check_server/conf/application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8092
# The task format in the engin_list is: <speech task>_<engine type>

2
tests/unit/server/online/tts/check_server/tts_online_application.yaml
Unescape View File

@ -3,7 +3,7 @@
#################################################################################
# SERVER SETTING #
#################################################################################
host: 127.0.0.1
host: 0.0.0.0
port: 8092
# The task format in the engin_list is: <speech task>_<engine type>

Write Preview
Loading…
Cancel
Save