Merge branch 'develop' into webdataset

.readthedocs.yml

@@ -21,5 +21,6 @@ python:
   version: 3.7
   install:
     - requirements: docs/requirements.txt
-
-
+    - method: setuptools
+      path: .
+  system_packages: true

README_cn.md

@@ -691,7 +691,7 @@ PaddleSpeech 的 **语音合成** 主要包含三个模块：文本前端、声
 - 非常感谢 [phecda-xu](https://github.com/phecda-xu)/[PaddleDubbing](https://github.com/phecda-xu/PaddleDubbing) 基于 PaddleSpeech 的 TTS 模型搭建带 GUI 操作界面的配音工具。
 - 非常感谢 [jerryuhoo](https://github.com/jerryuhoo)/[VTuberTalk](https://github.com/jerryuhoo/VTuberTalk) 基于 PaddleSpeech 的 TTS GUI 界面和基于 ASR 制作数据集的相关代码。
 
-- 非常感谢 [vpegasus](https://github.com/vpegasus)/[xuesebot](https://github.com/vpegasus/xuesebot) 基于 PaddleSpeech 的 ASR与TTS 设计的可听、说对话机器人
+- 非常感谢 [vpegasus](https://github.com/vpegasus)/[xuesebot](https://github.com/vpegasus/xuesebot) 基于 PaddleSpeech 的 ASR 与 TTS 设计的可听、说对话机器人。
 
 
 此外，PaddleSpeech 依赖于许多开源存储库。有关更多信息，请参阅 [references](./docs/source/reference.md)。

demos/audio_searching/requirements.txt

@@ -2,7 +2,7 @@ diskcache==5.2.1
 dtaidistance==2.3.1
 fastapi
 librosa==0.8.0
-numpy==1.21.0
+numpy==1.22.0
 pydantic
 pymilvus==2.0.1
 pymysql

demos/keyword_spotting/README.md

@@ -0,0 +1,79 @@
+([简体中文](./README_cn.md)|English)
+# KWS (Keyword Spotting)
+
+## Introduction
+KWS(Keyword Spotting) is a technique to recognize keyword from a giving speech audio.
+
+This demo is an implementation to recognize keyword from a specific audio file. It can be done by a single command or a few lines in python using `PaddleSpeech`. 
+
+## Usage
+### 1. Installation
+see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md).
+
+You can choose one way from easy, meduim and hard to install paddlespeech.
+
+### 2. Prepare Input File
+The input of this demo should be a WAV file(`.wav`), and the sample rate must be the same as the model.
+
+Here are sample files for this demo that can be downloaded:
+```bash
+wget -c https://paddlespeech.bj.bcebos.com/kws/hey_snips.wav https://paddlespeech.bj.bcebos.com/kws/non-keyword.wav
+```
+
+### 3. Usage
+- Command Line(Recommended)
+  ```bash
+  paddlespeech kws --input ./hey_snips.wav
+  paddlespeech kws --input ./non-keyword.wav
+  ```
+  
+  Usage:
+  ```bash
+  paddlespeech kws --help
+  ```
+  Arguments:
+  - `input`(required): Audio file to recognize.
+  - `threshold`：Score threshold for kws. Default: `0.8`.
+  - `model`: Model type of kws task. Default: `mdtc_heysnips`.
+  - `config`: Config of kws task. Use pretrained model when it is None. Default: `None`.
+  - `ckpt_path`: Model checkpoint. Use pretrained model when it is None. Default: `None`.
+  - `device`: Choose device to execute model inference. Default: default device of paddlepaddle in current environment.
+  - `verbose`: Show the log information.
+
+  Output:
+  ```bash
+  # Input file: ./hey_snips.wav
+  Score: 1.000, Threshold: 0.8, Is keyword: True
+  # Input file: ./non-keyword.wav
+  Score: 0.000, Threshold: 0.8, Is keyword: False
+  ```
+
+- Python API
+  ```python
+  import paddle
+  from paddlespeech.cli.kws import KWSExecutor
+
+  kws_executor = KWSExecutor()
+  result = kws_executor(
+      audio_file='./hey_snips.wav',
+      threshold=0.8,
+      model='mdtc_heysnips',
+      config=None,
+      ckpt_path=None,
+      device=paddle.get_device())
+  print('KWS Result: \n{}'.format(result))
+  ```
+
+  Output:
+  ```bash
+  KWS Result:
+  Score: 1.000, Threshold: 0.8, Is keyword: True
+  ```
+
+### 4.Pretrained Models
+
+Here is a list of pretrained models released by PaddleSpeech that can be used by command and python API:
+
+| Model | Language | Sample Rate
+| :--- | :---: | :---: |
+| mdtc_heysnips | en | 16k

demos/keyword_spotting/README_cn.md

@@ -0,0 +1,76 @@
+(简体中文|[English](./README.md))
+
+# 关键词识别
+## 介绍
+关键词识别是一项用于识别一段语音内是否包含特定的关键词。
+
+这个 demo 是一个从给定音频文件识别特定关键词的实现，它可以通过使用 `PaddleSpeech` 的单个命令或 python 中的几行代码来实现。
+## 使用方法
+### 1. 安装
+请看[安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install_cn.md)。
+
+你可以从 easy，medium，hard 三中方式中选择一种方式安装。
+
+### 2. 准备输入
+这个 demo 的输入应该是一个 WAV 文件（`.wav`），并且采样率必须与模型的采样率相同。
+
+可以下载此 demo 的示例音频：
+```bash
+wget -c https://paddlespeech.bj.bcebos.com/kws/hey_snips.wav https://paddlespeech.bj.bcebos.com/kws/non-keyword.wav
+```
+### 3. 使用方法
+- 命令行 (推荐使用)
+  ```bash
+  paddlespeech kws --input ./hey_snips.wav
+  paddlespeech kws --input ./non-keyword.wav
+  ```
+  
+  使用方法：
+  ```bash
+  paddlespeech kws --help
+  ```
+  参数：
+  - `input`(必须输入)：用于识别关键词的音频文件。
+  - `threshold`：用于判别是包含关键词的得分阈值，默认值：`0.8`。
+  - `model`：KWS 任务的模型，默认值：`mdtc_heysnips`。
+  - `config`：KWS 任务的参数文件，若不设置则使用预训练模型中的默认配置，默认值：`None`。
+  - `ckpt_path`：模型参数文件，若不设置则下载预训练模型使用，默认值：`None`。
+  - `device`：执行预测的设备，默认值：当前系统下 paddlepaddle 的默认 device。
+  - `verbose`: 如果使用，显示 logger 信息。
+
+  输出：
+  ```bash
+  # 输入为 ./hey_snips.wav
+  Score: 1.000, Threshold: 0.8, Is keyword: True
+  # 输入为 ./non-keyword.wav
+  Score: 0.000, Threshold: 0.8, Is keyword: False
+  ```
+
+- Python API
+  ```python
+  import paddle
+  from paddlespeech.cli.kws import KWSExecutor
+
+  kws_executor = KWSExecutor()
+  result = kws_executor(
+      audio_file='./hey_snips.wav',
+      threshold=0.8,
+      model='mdtc_heysnips',
+      config=None,
+      ckpt_path=None,
+      device=paddle.get_device())
+  print('KWS Result: \n{}'.format(result))
+  ```
+
+  输出：
+  ```bash
+  KWS Result:
+  Score: 1.000, Threshold: 0.8, Is keyword: True
+  ```
+
+### 4.预训练模型
+以下是 PaddleSpeech 提供的可以被命令行和 python API 使用的预训练模型列表：
+
+| 模型 | 语言 | 采样率
+| :--- | :---: | :---: |
+| mdtc_heysnips | en | 16k

demos/keyword_spotting/run.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+wget -c https://paddlespeech.bj.bcebos.com/kws/hey_snips.wav https://paddlespeech.bj.bcebos.com/kws/non-keyword.wav
+
+# kws
+paddlespeech kws --input ./hey_snips.wav
+paddlespeech kws --input non-keyword.wav

demos/speech_web/README_cn.md

@@ -24,6 +24,12 @@ PaddleSpeechDemo是一个以PaddleSpeech的语音交互功能为主体开发的D
 # 安装环境
 cd speech_server
 pip install -r requirements.txt
+
+# 下载 ie 模型，针对地点进行微调，效果更好，不下载的话会使用其它版本，效果没有这个好
+cd source
+mkdir model
+cd model
+wget https://bj.bcebos.com/paddlenlp/applications/speech-cmd-analysis/finetune/model_state.pdparams
 ```
 
 
@@ -61,59 +67,6 @@ yarn dev --port 8011
 ```
 
 默认配置下，前端中配置的后台地址信息是localhost，确保后端服务器和打开页面的游览器在同一台机器上，不在一台机器的配置方式见下方的FAQ：【后端如果部署在其它机器或者别的端口如何修改】
-
-## Docker启动
-
-### 后端docker
-后端docker使用[paddlepaddle官方docker](https://www.paddlepaddle.org.cn),这里演示CPU版本
-```
-# 拉取PaddleSpeech项目
-cd PaddleSpeechServer
-git clone https://github.com/PaddlePaddle/PaddleSpeech.git
-
-# 拉取镜像
-docker pull registry.baidubce.com/paddlepaddle/paddle:2.3.0
-
-# 启动容器
-docker run --name paddle -it -p 8010:8010 -v $PWD:/paddle registry.baidubce.com/paddlepaddle/paddle:2.3.0 /bin/bash
-
-# 进入容器
-cd /paddle
-
-# 安装依赖
-pip install -r requirements
-
-# 启动服务
-python main --port 8010
-
-```
-
-### 前端docker
-
-前端docker直接使用[node官方的docker](https://hub.docker.com/_/node)即可
-
-```shell
-docker pull node
-```
-
-镜像中安装依赖
-
-```shell
-cd PaddleSpeechWebClient
-# 映射外部8011端口
-docker run -it -p 8011:8011 -v $PWD:/paddle node:latest bin/bash
-# 进入容器中
-cd /paddle
-# 安装依赖
-yarn install
-# 启动前端
-yarn dev --port 8011
-```
-
-
-
-
-
 ## FAQ 
 
 #### Q: 如何安装node.js
@@ -126,7 +79,7 @@ A：后端的配置地址有分散在两个文件中
 
 修改第一个文件`PaddleSpeechWebClient/vite.config.js`
 
-```json
+```
 server: {
     host: "0.0.0.0",
     proxy: {
@@ -141,7 +94,7 @@ server: {
 
 修改第二个文件`PaddleSpeechWebClient/src/api/API.js`（Websocket代理配置失败，所以需要在这个文件中修改）
 
-```javascript
+```
 // websocket （这里改成后端所在的接口）
 CHAT_SOCKET_RECORD: 'ws://localhost:8010/ws/asr/offlineStream', // ChatBot websocket 接口
 ASR_SOCKET_RECORD: 'ws://localhost:8010/ws/asr/onlineStream',  // Stream ASR 接口

demos/speech_web/speech_server/main.py

@@ -30,7 +30,7 @@ from src.robot import Robot
 from src.WebsocketManeger import ConnectionManager
 from src.SpeechBase.vpr import VPR
 
-from paddlespeech.server.engine.asr.online.asr_engine import PaddleASRConnectionHanddler
+from paddlespeech.server.engine.asr.online.python.asr_engine import PaddleASRConnectionHanddler
 from paddlespeech.server.utils.audio_process import float2pcm
 
 

demos/speech_web/speech_server/src/AudioManeger.py

@@ -147,27 +147,4 @@ class AudioMannger:
         self.is_pause = False
     
     
-if __name__ == '__main__':
-    from robot import Robot
-
-    chatbot = Robot()
-    chatbot.init()
-    audio_manger = AudioMannger(chatbot)
-    
-    file_list = [
-        "source/20220418145230qbenc.pcm",
-    ]
-    
-    for file in file_list:
-        with open(file, "rb") as f:
-            pcm_bin = f.read()
-            print(len(pcm_bin))
-        asr_ = audio_manger.stream_asr(pcm_bin=pcm_bin)
-        print(asr_)
-    
-    print(audio_manger.end())
-    
-    print(chatbot.speech2text("source/20220418145230zrxia.wav"))
-    
-    
     

demos/speech_web/speech_server/src/SpeechBase/asr.py

@@ -4,8 +4,8 @@ import paddle
 import librosa
 import soundfile
 
-from paddlespeech.server.engine.asr.online.asr_engine import ASREngine
-from paddlespeech.server.engine.asr.online.asr_engine import PaddleASRConnectionHanddler
+from paddlespeech.server.engine.asr.online.python.asr_engine import ASREngine
+from paddlespeech.server.engine.asr.online.python.asr_engine import PaddleASRConnectionHanddler
 from paddlespeech.server.utils.config import get_config
 
 def readWave(samples):
@@ -60,28 +60,3 @@ class ASR:
             return asr_results
 
         
-if __name__ == '__main__':
-    config_path = r"../../PaddleSpeech/paddlespeech/server/conf/ws_conformer_application.yaml"
-    
-    wav_path = r"../../source/demo/demo_16k.wav"
-    samples, sample_rate = soundfile.read(wav_path, dtype='int16')
-    
-    asr = ASR(config_path=config_path)
-    end_result = asr.offlineASR(samples=samples, sample_rate=sample_rate)
-    print("端到端识别结果：", end_result)
-    
-    for sub_wav in readWave(samples=samples):
-        # print(sub_wav)
-        message = sub_wav.tobytes()
-        offline_result = asr.onlineASR(message, is_finished=False)
-        print("流式识别结果: ", offline_result)
-    offline_result = asr.onlineASR(is_finished=True)
-    print("流式识别结果: ", offline_result)
-
-
-    
-    
-    
-    
-
-        

demos/speech_web/speech_server/src/SpeechBase/nlp.py

@@ -20,9 +20,4 @@ class NLP:
         result = self.ie_model(text)
         return result
 
-if __name__ == '__main__':
-    ie_model_path = "../../source/model/"
-    nlp = NLP(ie_model_path=ie_model_path)
-    text = "今天早上我从大牛坊去百度科技园花了七百块钱"
-    print(nlp.ie(text))
     

demos/speech_web/speech_server/src/SpeechBase/sql_helper.py

@@ -114,39 +114,3 @@ class DataBase(object):
         vc = np.frombuffer(b, dtype=dtype)
         return vc
     
-if __name__ == '__main__':
-    db_path = "../../source/db/vpr.sqlite"
-    db = DataBase(db_path)
-    
-    # 准备数据
-    import numpy as np
-    vector = np.random.randn((192)).astype(np.float32).tobytes()
-    vector_base64 = base64.b64encode(vector).decode('utf8')
-    username = "sss"
-    wav_path = r"../../source/demo/demo_16k.wav"
-    
-    # 插入数据
-    db.insert_one(username, vector_base64, wav_path)
-    
-    # 查询数据
-    res_all = db.select_all()
-    print("res_all: ", res_all)
-    
-    s_id = res_all[0]['id']
-    res_id = db.select_by_id(s_id)
-    print("res_id: ", res_id)
-    
-    res_uername = db.select_by_username(username)
-    print("res_username: ", res_uername)
-    
-    # base64还原
-    b = base64.b64decode(res_uername[0]['vector'])
-    vc = np.frombuffer(b, dtype=np.float32)
-    print(vc)
-    
-    # 删除数据
-    db.drop_by_username(username)
-    res_all = db.select_all()
-    print("删除后 res_all: ", res_all)
-    db.drop_all()
-    

demos/speech_web/speech_server/src/SpeechBase/tts.py

@@ -7,7 +7,8 @@
 # 4. 流式推理
 
 import base64
-
+import math
+import logging
 import numpy as np
 from paddlespeech.server.utils.onnx_infer import get_sess
 from paddlespeech.t2s.frontend.zh_frontend import Frontend
@@ -17,14 +18,14 @@ from paddlespeech.server.utils.config import get_config
 
 from paddlespeech.server.engine.tts.online.onnx.tts_engine import TTSEngine
 
-
 class TTS:
     def __init__(self, config_path):
         self.config = get_config(config_path)['tts_online-onnx']
         self.config['voc_block'] = 36
-        self.engine =  TTSEngine()
+        self.engine = TTSEngine()
         self.engine.init(self.config)
-        self.engine.warm_up()
+        self.executor = self.engine.executor
+        #self.engine.warm_up()
         
         # 前端初始化
         self.frontend = Frontend(
@@ -81,8 +82,105 @@ class TTS:
         return wavs
     
     def streamTTS(self, text):
-        for sub_wav_base64 in self.engine.run(sentence=text):
-            yield sub_wav_base64
+
+        get_tone_ids = False
+        merge_sentences = False
+
+        # front 
+        input_ids = self.frontend.get_input_ids(
+                text,
+                merge_sentences=merge_sentences,
+                get_tone_ids=get_tone_ids)
+        phone_ids = input_ids["phone_ids"]
+
+        for i in range(len(phone_ids)):
+            part_phone_ids = phone_ids[i].numpy()
+            voc_chunk_id = 0
+
+            # fastspeech2_csmsc
+            if self.config.am == "fastspeech2_csmsc_onnx":
+                # am 
+                mel = self.executor.am_sess.run(
+                    output_names=None, input_feed={'text': part_phone_ids})
+                mel = mel[0]
+
+                # voc streaming
+                mel_chunks = get_chunks(mel, self.config.voc_block, self.config.voc_pad, "voc")
+                voc_chunk_num = len(mel_chunks)
+                for i, mel_chunk in enumerate(mel_chunks):
+                    sub_wav = self.executor.voc_sess.run(
+                        output_names=None, input_feed={'logmel': mel_chunk})
+                    sub_wav = self.depadding(sub_wav[0], voc_chunk_num, i,
+                                             self.config.voc_block, self.config.voc_pad,
+                                             self.config.voc_upsample)
+
+                    yield self.after_process(sub_wav)
+
+            # fastspeech2_cnndecoder_csmsc 
+            elif self.config.am == "fastspeech2_cnndecoder_csmsc_onnx":
+                # am 
+                orig_hs = self.executor.am_encoder_infer_sess.run(
+                    None, input_feed={'text': part_phone_ids})
+                orig_hs = orig_hs[0]
+
+                # streaming voc chunk info
+                mel_len = orig_hs.shape[1]
+                voc_chunk_num = math.ceil(mel_len / self.config.voc_block)
+                start = 0
+                end = min(self.config.voc_block + self.config.voc_pad, mel_len)
+
+                # streaming am
+                hss = get_chunks(orig_hs, self.config.am_block, self.config.am_pad, "am")
+                am_chunk_num = len(hss)
+                for i, hs in enumerate(hss):
+                    am_decoder_output = self.executor.am_decoder_sess.run(
+                        None, input_feed={'xs': hs})
+                    am_postnet_output = self.executor.am_postnet_sess.run(
+                        None,
+                        input_feed={
+                            'xs': np.transpose(am_decoder_output[0], (0, 2, 1))
+                        })
+                    am_output_data = am_decoder_output + np.transpose(
+                        am_postnet_output[0], (0, 2, 1))
+                    normalized_mel = am_output_data[0][0]
+
+                    sub_mel = denorm(normalized_mel, self.executor.am_mu,
+                                     self.executor.am_std)
+                    sub_mel = self.depadding(sub_mel, am_chunk_num, i,
+                                             self.config.am_block, self.config.am_pad, 1)
+
+                    if i == 0:
+                        mel_streaming = sub_mel
+                    else:
+                        mel_streaming = np.concatenate(
+                            (mel_streaming, sub_mel), axis=0)
+
+                    # streaming voc
+                    # 当流式AM推理的mel帧数大于流式voc推理的chunk size，开始进行流式voc 推理
+                    while (mel_streaming.shape[0] >= end and
+                           voc_chunk_id < voc_chunk_num):
+                        voc_chunk = mel_streaming[start:end, :]
+
+                        sub_wav = self.executor.voc_sess.run(
+                            output_names=None, input_feed={'logmel': voc_chunk})
+                        sub_wav = self.depadding(
+                            sub_wav[0], voc_chunk_num, voc_chunk_id,
+                            self.config.voc_block, self.config.voc_pad, self.config.voc_upsample)
+
+                        yield self.after_process(sub_wav)
+
+                        voc_chunk_id += 1
+                        start = max(
+                            0, voc_chunk_id * self.config.voc_block - self.config.voc_pad)
+                        end = min(
+                            (voc_chunk_id + 1) * self.config.voc_block + self.config.voc_pad,
+                            mel_len)
+
+            else:
+                logging.error(
+                    "Only support fastspeech2_csmsc or fastspeech2_cnndecoder_csmsc on streaming tts."
+                ) 
+
     
     def streamTTSBytes(self, text):
         for wav in self.engine.executor.infer(
@@ -106,16 +204,6 @@ class TTS:
         # 用 TVM 优化
         pass
 
-if __name__ == '__main__':
-    text = "啊哈哈哈哈哈哈啊哈哈哈哈哈哈啊哈哈哈哈哈哈啊哈哈哈哈哈哈啊哈哈哈哈哈哈"
-    config_path="../../PaddleSpeech/demos/streaming_tts_server/conf/tts_online_application.yaml"
-    tts = TTS(config_path)
-    
-    for sub_wav in tts.streamTTS(text):
-        print("sub_wav_base64: ", len(sub_wav))
-    
-    end_wav = tts.offlineTTS(text)
-    print(end_wav)
     
     
         

demos/speech_web/speech_server/src/SpeechBase/vpr.py

@@ -116,37 +116,3 @@ class VPR:
         # 清空 faiss
         self.index_ip.reset()
         
-    
-
-if __name__ == '__main__':
-    
-    db_path = "../../source/db/vpr.sqlite"
-    dim = 192
-    top_k = 5
-    vpr = VPR(db_path, dim, top_k)
-    
-    # 准备测试数据
-    username = "sss"
-    wav_path = r"../../source/demo/demo_16k.wav"
-    
-    # 注册声纹
-    vpr.vpr_enroll(username, wav_path)
-    
-    # 获取数据
-    print(vpr.vpr_list())
-    
-    # 识别声纹
-    recolist = vpr.vpr_recog(wav_path)
-    print(recolist)
-    
-    # 通过 id 获取数据
-    idx = recolist[0][1]
-    print(vpr.vpr_data(idx))
-
-    # 删除声纹
-    vpr.vpr_del(username)
-    vpr.vpr_droptable()
-    
-    
-    
-    

demos/speech_web/speech_server/src/SpeechBase/vpr_encode.py

@@ -1,4 +1,4 @@
-from paddlespeech.cli import VectorExecutor
+from paddlespeech.cli.vector import VectorExecutor
 import numpy as np
 import logging
 
@@ -17,10 +17,4 @@ def get_audio_embedding(path):
         logging.error(f"Error with embedding:{e}")
         return None
 
-if __name__ == '__main__':
-    audio_path = r"../../source/demo/demo_16k.wav"
-    emb = get_audio_embedding(audio_path)
-    print(emb.shape)
-    print(emb.dtype)
-    print(type(emb))
     

demos/speech_web/speech_server/src/robot.py

@@ -35,7 +35,7 @@ class Robot:
             
         # asr model初始化
         self.asr_model(asr_init_path, model=self.asr_name,lang='zh',
-                 sample_rate=16000)
+                 sample_rate=16000, force_yes=True)
         
     
     def speech2text(self, audio_file):
@@ -67,27 +67,4 @@ class Robot:
         result = self.nlp.ie(text)
         return result
     
-if __name__ == '__main__':
-    tts_config = "../PaddleSpeech/demos/streaming_tts_server/conf/tts_online_application.yaml"
-    asr_config = "../PaddleSpeech/demos/streaming_asr_server/conf/ws_conformer_application.yaml"
-    demo_wav = "../source/demo/demo_16k.wav"
-    ie_model_path = "../source/model"
-    tts_wav = "../source/demo/tts.wav"
-    text = "今天天气真不错"
-    ie_text = "今天晚上我从大牛坊出发去三里屯花了六十五块钱"
-    
-    
-    robot = Robot(asr_config, tts_config, asr_init_path=demo_wav)
-    res = robot.speech2text(demo_wav)
-    print(res)
-    
-    res = robot.chat(text)
-    print(res)
-    print("tts offline")
-    robot.text2speech(res, tts_wav)
-    
-    print("ie test")
-    res = robot.ie(ie_text)
-    print(res)
-    
     

docs/requirements.txt

@@ -5,3 +5,46 @@ sphinx
 sphinx-autobuild
 sphinx-markdown-tables
 sphinx_rtd_theme
+paddlepaddle>=2.2.2
+editdistance
+g2p_en
+g2pM
+h5py
+inflect
+jieba
+jsonlines
+kaldiio
+librosa==0.8.1
+loguru
+matplotlib
+nara_wpe
+onnxruntime
+pandas
+paddlenlp
+paddlespeech_feat
+praatio==5.0.0
+pypinyin
+pypinyin-dict
+python-dateutil
+pyworld==0.2.12
+resampy==0.2.2
+sacrebleu
+scipy
+sentencepiece~=0.1.96
+soundfile~=0.10
+textgrid
+timer
+tqdm
+typeguard
+visualdl
+webrtcvad
+yacs~=0.1.8
+prettytable
+zhon
+colorlog
+pathos == 0.2.8
+fastapi
+websockets
+keyboard
+uvicorn
+pattern_singleton

docs/source/api/modules.rst

@@ -0,0 +1,7 @@
+paddlespeech
+============
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech

docs/source/api/paddlespeech.audio.backends.rst

@@ -0,0 +1,16 @@
+paddlespeech.audio.backends package
+===================================
+
+.. automodule:: paddlespeech.audio.backends
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.backends.soundfile_backend
+   paddlespeech.audio.backends.sox_backend

docs/source/api/paddlespeech.audio.backends.soundfile_backend.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.backends.soundfile\_backend module
+=====================================================
+
+.. automodule:: paddlespeech.audio.backends.soundfile_backend
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.backends.sox_backend.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.backends.sox\_backend module
+===============================================
+
+.. automodule:: paddlespeech.audio.backends.sox_backend
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.compliance.kaldi.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.compliance.kaldi module
+==========================================
+
+.. automodule:: paddlespeech.audio.compliance.kaldi
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.compliance.librosa.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.compliance.librosa module
+============================================
+
+.. automodule:: paddlespeech.audio.compliance.librosa
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.compliance.rst

@@ -0,0 +1,16 @@
+paddlespeech.audio.compliance package
+=====================================
+
+.. automodule:: paddlespeech.audio.compliance
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.compliance.kaldi
+   paddlespeech.audio.compliance.librosa

docs/source/api/paddlespeech.audio.datasets.dataset.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.dataset module
+==========================================
+
+.. automodule:: paddlespeech.audio.datasets.dataset
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.esc50.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.esc50 module
+========================================
+
+.. automodule:: paddlespeech.audio.datasets.esc50
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.gtzan.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.gtzan module
+========================================
+
+.. automodule:: paddlespeech.audio.datasets.gtzan
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.hey_snips.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.hey\_snips module
+=============================================
+
+.. automodule:: paddlespeech.audio.datasets.hey_snips
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.rirs_noises.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.rirs\_noises module
+===============================================
+
+.. automodule:: paddlespeech.audio.datasets.rirs_noises
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.rst

@@ -0,0 +1,22 @@
+paddlespeech.audio.datasets package
+===================================
+
+.. automodule:: paddlespeech.audio.datasets
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.datasets.dataset
+   paddlespeech.audio.datasets.esc50
+   paddlespeech.audio.datasets.gtzan
+   paddlespeech.audio.datasets.hey_snips
+   paddlespeech.audio.datasets.rirs_noises
+   paddlespeech.audio.datasets.tess
+   paddlespeech.audio.datasets.urban_sound
+   paddlespeech.audio.datasets.voxceleb

docs/source/api/paddlespeech.audio.datasets.tess.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.tess module
+=======================================
+
+.. automodule:: paddlespeech.audio.datasets.tess
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.urban_sound.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.urban\_sound module
+===============================================
+
+.. automodule:: paddlespeech.audio.datasets.urban_sound
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.datasets.voxceleb.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.datasets.voxceleb module
+===========================================
+
+.. automodule:: paddlespeech.audio.datasets.voxceleb
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.features.layers.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.features.layers module
+=========================================
+
+.. automodule:: paddlespeech.audio.features.layers
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.features.rst

@@ -0,0 +1,15 @@
+paddlespeech.audio.features package
+===================================
+
+.. automodule:: paddlespeech.audio.features
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.features.layers

docs/source/api/paddlespeech.audio.functional.functional.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.functional.functional module
+===============================================
+
+.. automodule:: paddlespeech.audio.functional.functional
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.functional.rst

@@ -0,0 +1,16 @@
+paddlespeech.audio.functional package
+=====================================
+
+.. automodule:: paddlespeech.audio.functional
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.functional.functional
+   paddlespeech.audio.functional.window

docs/source/api/paddlespeech.audio.functional.window.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.functional.window module
+===========================================
+
+.. automodule:: paddlespeech.audio.functional.window
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.io.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.io package
+=============================
+
+.. automodule:: paddlespeech.audio.io
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.metric.eer.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.metric.eer module
+====================================
+
+.. automodule:: paddlespeech.audio.metric.eer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.metric.rst

@@ -0,0 +1,15 @@
+paddlespeech.audio.metric package
+=================================
+
+.. automodule:: paddlespeech.audio.metric
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.metric.eer

docs/source/api/paddlespeech.audio.rst

@@ -0,0 +1,23 @@
+paddlespeech.audio package
+==========================
+
+.. automodule:: paddlespeech.audio
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.backends
+   paddlespeech.audio.compliance
+   paddlespeech.audio.datasets
+   paddlespeech.audio.features
+   paddlespeech.audio.functional
+   paddlespeech.audio.io
+   paddlespeech.audio.metric
+   paddlespeech.audio.sox_effects
+   paddlespeech.audio.utils

docs/source/api/paddlespeech.audio.sox_effects.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.sox\_effects package
+=======================================
+
+.. automodule:: paddlespeech.audio.sox_effects
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.utils.download.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.utils.download module
+========================================
+
+.. automodule:: paddlespeech.audio.utils.download
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.utils.error.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.utils.error module
+=====================================
+
+.. automodule:: paddlespeech.audio.utils.error
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.utils.log.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.utils.log module
+===================================
+
+.. automodule:: paddlespeech.audio.utils.log
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.utils.numeric.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.utils.numeric module
+=======================================
+
+.. automodule:: paddlespeech.audio.utils.numeric
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.audio.utils.rst

@@ -0,0 +1,19 @@
+paddlespeech.audio.utils package
+================================
+
+.. automodule:: paddlespeech.audio.utils
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio.utils.download
+   paddlespeech.audio.utils.error
+   paddlespeech.audio.utils.log
+   paddlespeech.audio.utils.numeric
+   paddlespeech.audio.utils.time

docs/source/api/paddlespeech.audio.utils.time.rst

@@ -0,0 +1,7 @@
+paddlespeech.audio.utils.time module
+====================================
+
+.. automodule:: paddlespeech.audio.utils.time
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.asr.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.asr.infer module
+=================================
+
+.. automodule:: paddlespeech.cli.asr.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.asr.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.asr package
+============================
+
+.. automodule:: paddlespeech.cli.asr
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.asr.infer

docs/source/api/paddlespeech.cli.base_commands.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.base\_commands module
+======================================
+
+.. automodule:: paddlespeech.cli.base_commands
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.cls.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.cls.infer module
+=================================
+
+.. automodule:: paddlespeech.cli.cls.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.cls.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.cls package
+============================
+
+.. automodule:: paddlespeech.cli.cls
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.cls.infer

docs/source/api/paddlespeech.cli.download.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.download module
+================================
+
+.. automodule:: paddlespeech.cli.download
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.entry.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.entry module
+=============================
+
+.. automodule:: paddlespeech.cli.entry
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.executor.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.executor module
+================================
+
+.. automodule:: paddlespeech.cli.executor
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.kws.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.kws.infer module
+=================================
+
+.. automodule:: paddlespeech.cli.kws.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.kws.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.kws package
+============================
+
+.. automodule:: paddlespeech.cli.kws
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.kws.infer

docs/source/api/paddlespeech.cli.log.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.log module
+===========================
+
+.. automodule:: paddlespeech.cli.log
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.rst

@@ -0,0 +1,34 @@
+paddlespeech.cli package
+========================
+
+.. automodule:: paddlespeech.cli
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.asr
+   paddlespeech.cli.cls
+   paddlespeech.cli.kws
+   paddlespeech.cli.st
+   paddlespeech.cli.text
+   paddlespeech.cli.tts
+   paddlespeech.cli.vector
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.base_commands
+   paddlespeech.cli.download
+   paddlespeech.cli.entry
+   paddlespeech.cli.executor
+   paddlespeech.cli.log
+   paddlespeech.cli.utils

docs/source/api/paddlespeech.cli.st.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.st.infer module
+================================
+
+.. automodule:: paddlespeech.cli.st.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.st.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.st package
+===========================
+
+.. automodule:: paddlespeech.cli.st
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.st.infer

docs/source/api/paddlespeech.cli.text.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.text.infer module
+==================================
+
+.. automodule:: paddlespeech.cli.text.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.text.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.text package
+=============================
+
+.. automodule:: paddlespeech.cli.text
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.text.infer

docs/source/api/paddlespeech.cli.tts.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.tts.infer module
+=================================
+
+.. automodule:: paddlespeech.cli.tts.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.tts.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.tts package
+============================
+
+.. automodule:: paddlespeech.cli.tts
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.tts.infer

docs/source/api/paddlespeech.cli.utils.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.utils module
+=============================
+
+.. automodule:: paddlespeech.cli.utils
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.vector.infer.rst

@@ -0,0 +1,7 @@
+paddlespeech.cli.vector.infer module
+====================================
+
+.. automodule:: paddlespeech.cli.vector.infer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cli.vector.rst

@@ -0,0 +1,15 @@
+paddlespeech.cli.vector package
+===============================
+
+.. automodule:: paddlespeech.cli.vector
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cli.vector.infer

docs/source/api/paddlespeech.cls.exps.panns.deploy.predict.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.exps.panns.deploy.predict module
+=================================================
+
+.. automodule:: paddlespeech.cls.exps.panns.deploy.predict
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.exps.panns.deploy.rst

@@ -0,0 +1,15 @@
+paddlespeech.cls.exps.panns.deploy package
+==========================================
+
+.. automodule:: paddlespeech.cls.exps.panns.deploy
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.exps.panns.deploy.predict

docs/source/api/paddlespeech.cls.exps.panns.export_model.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.exps.panns.export\_model module
+================================================
+
+.. automodule:: paddlespeech.cls.exps.panns.export_model
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.exps.panns.predict.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.exps.panns.predict module
+==========================================
+
+.. automodule:: paddlespeech.cls.exps.panns.predict
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.exps.panns.rst

@@ -0,0 +1,25 @@
+paddlespeech.cls.exps.panns package
+===================================
+
+.. automodule:: paddlespeech.cls.exps.panns
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.exps.panns.deploy
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.exps.panns.export_model
+   paddlespeech.cls.exps.panns.predict
+   paddlespeech.cls.exps.panns.train

docs/source/api/paddlespeech.cls.exps.panns.train.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.exps.panns.train module
+========================================
+
+.. automodule:: paddlespeech.cls.exps.panns.train
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.exps.rst

@@ -0,0 +1,15 @@
+paddlespeech.cls.exps package
+=============================
+
+.. automodule:: paddlespeech.cls.exps
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.exps.panns

docs/source/api/paddlespeech.cls.models.panns.classifier.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.models.panns.classifier module
+===============================================
+
+.. automodule:: paddlespeech.cls.models.panns.classifier
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.models.panns.panns.rst

@@ -0,0 +1,7 @@
+paddlespeech.cls.models.panns.panns module
+==========================================
+
+.. automodule:: paddlespeech.cls.models.panns.panns
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.cls.models.panns.rst

@@ -0,0 +1,16 @@
+paddlespeech.cls.models.panns package
+=====================================
+
+.. automodule:: paddlespeech.cls.models.panns
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.models.panns.classifier
+   paddlespeech.cls.models.panns.panns

docs/source/api/paddlespeech.cls.models.rst

@@ -0,0 +1,15 @@
+paddlespeech.cls.models package
+===============================
+
+.. automodule:: paddlespeech.cls.models
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.models.panns

docs/source/api/paddlespeech.cls.rst

@@ -0,0 +1,16 @@
+paddlespeech.cls package
+========================
+
+.. automodule:: paddlespeech.cls
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.cls.exps
+   paddlespeech.cls.models

docs/source/api/paddlespeech.kws.models.loss.rst

@@ -0,0 +1,7 @@
+paddlespeech.kws.models.loss module
+===================================
+
+.. automodule:: paddlespeech.kws.models.loss
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.kws.models.mdtc.rst

@@ -0,0 +1,7 @@
+paddlespeech.kws.models.mdtc module
+===================================
+
+.. automodule:: paddlespeech.kws.models.mdtc
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.kws.models.rst

@@ -0,0 +1,16 @@
+paddlespeech.kws.models package
+===============================
+
+.. automodule:: paddlespeech.kws.models
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.kws.models.loss
+   paddlespeech.kws.models.mdtc

docs/source/api/paddlespeech.kws.rst

@@ -0,0 +1,15 @@
+paddlespeech.kws package
+========================
+
+.. automodule:: paddlespeech.kws
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.kws.models

docs/source/api/paddlespeech.rst

@@ -0,0 +1,23 @@
+paddlespeech package
+====================
+
+.. automodule:: paddlespeech
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.audio
+   paddlespeech.cli
+   paddlespeech.cls
+   paddlespeech.kws
+   paddlespeech.s2t
+   paddlespeech.server
+   paddlespeech.t2s
+   paddlespeech.text
+   paddlespeech.vector

docs/source/api/paddlespeech.s2t.decoders.beam_search.batch_beam_search.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.beam\_search.batch\_beam\_search module
+=================================================================
+
+.. automodule:: paddlespeech.s2t.decoders.beam_search.batch_beam_search
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.beam_search.beam_search.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.beam\_search.beam\_search module
+==========================================================
+
+.. automodule:: paddlespeech.s2t.decoders.beam_search.beam_search
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.beam_search.rst

@@ -0,0 +1,16 @@
+paddlespeech.s2t.decoders.beam\_search package
+==============================================
+
+.. automodule:: paddlespeech.s2t.decoders.beam_search
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.s2t.decoders.beam_search.batch_beam_search
+   paddlespeech.s2t.decoders.beam_search.beam_search

docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.decoders_deprecated.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.ctcdecoder.decoders\_deprecated module
+================================================================
+
+.. automodule:: paddlespeech.s2t.decoders.ctcdecoder.decoders_deprecated
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.rst

@@ -0,0 +1,17 @@
+paddlespeech.s2t.decoders.ctcdecoder package
+============================================
+
+.. automodule:: paddlespeech.s2t.decoders.ctcdecoder
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.s2t.decoders.ctcdecoder.decoders_deprecated
+   paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated
+   paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper

docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.ctcdecoder.scorer\_deprecated module
+==============================================================
+
+.. automodule:: paddlespeech.s2t.decoders.ctcdecoder.scorer_deprecated
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.ctcdecoder.swig\_wrapper module
+=========================================================
+
+.. automodule:: paddlespeech.s2t.decoders.ctcdecoder.swig_wrapper
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.recog.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.recog module
+======================================
+
+.. automodule:: paddlespeech.s2t.decoders.recog
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.recog_bin.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.recog\_bin module
+===========================================
+
+.. automodule:: paddlespeech.s2t.decoders.recog_bin
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.rst

@@ -0,0 +1,27 @@
+paddlespeech.s2t.decoders package
+=================================
+
+.. automodule:: paddlespeech.s2t.decoders
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.s2t.decoders.beam_search
+   paddlespeech.s2t.decoders.ctcdecoder
+   paddlespeech.s2t.decoders.scorers
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   paddlespeech.s2t.decoders.recog
+   paddlespeech.s2t.decoders.recog_bin
+   paddlespeech.s2t.decoders.utils

docs/source/api/paddlespeech.s2t.decoders.scorers.ctc.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.scorers.ctc module
+============================================
+
+.. automodule:: paddlespeech.s2t.decoders.scorers.ctc
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.scorers.ctc_prefix_score.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.scorers.ctc\_prefix\_score module
+===========================================================
+
+.. automodule:: paddlespeech.s2t.decoders.scorers.ctc_prefix_score
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/api/paddlespeech.s2t.decoders.scorers.length_bonus.rst

@@ -0,0 +1,7 @@
+paddlespeech.s2t.decoders.scorers.length\_bonus module
+======================================================
+
+.. automodule:: paddlespeech.s2t.decoders.scorers.length_bonus
+   :members:
+   :undoc-members:
+   :show-inheritance: