diff --git a/audio/setup.py b/audio/setup.py index ffee6f9d..ec67c81d 100644 --- a/audio/setup.py +++ b/audio/setup.py @@ -19,7 +19,7 @@ from setuptools.command.install import install from setuptools.command.test import test # set the version here -VERSION = '1.0.0a' +VERSION = '0.0.0' # Inspired by the example at https://pytest.org/latest/goodpractises.html diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index 0323d398..3df93238 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -10,7 +10,7 @@ This demo is an implementation of starting the voice service and accessing the s ### 1. Installation see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -It is recommended to use **paddlepaddle 2.2.1** or above. +It is recommended to use **paddlepaddle 2.2.2** or above. You can choose one way from meduim and hard to install paddlespeech. ### 2. Prepare config File @@ -18,6 +18,7 @@ The configuration file can be found in `conf/application.yaml` . Among them, `engine_list` indicates the speech engine that will be included in the service to be started, in the format of `_`. At present, the speech tasks integrated by the service include: asr (speech recognition), tts (text to sppech) and cls (audio classification). Currently the engine type supports two forms: python and inference (Paddle Inference) +**Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address. The input of ASR client demo should be a WAV file(`.wav`), and the sample rate must be the same as the model. @@ -51,8 +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://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) + 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) ``` @@ -74,8 +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://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) + 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) ``` diff --git a/demos/speech_server/README_cn.md b/demos/speech_server/README_cn.md index 4a7c7447..55fc6b34 100644 --- a/demos/speech_server/README_cn.md +++ b/demos/speech_server/README_cn.md @@ -1,17 +1,17 @@ -([简体中文](./README_cn.md)|English) +(简体中文|[English](./README.md)) # 语音服务 ## 介绍 -这个demo是一个启动语音服务和访问服务的实现。 它可以通过使用`paddlespeech_server` 和 `paddlespeech_client`的单个命令或 python 的几行代码来实现。 +这个demo是一个启动离线语音服务和访问服务的实现。它可以通过使用`paddlespeech_server` 和 `paddlespeech_client`的单个命令或 python 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.md). -推荐使用 **paddlepaddle 2.2.1** 或以上版本。 -你可以从 medium，hard 三中方式中选择一种方式安装 PaddleSpeech。 +推荐使用 **paddlepaddle 2.2.2** 或以上版本。 +你可以从 medium，hard 两种方式中选择一种方式安装 PaddleSpeech。 ### 2. 准备配置文件 @@ -19,9 +19,10 @@ 其中，`engine_list`表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。 目前服务集成的语音任务有： asr(语音识别)、tts(语音合成)以及cls(音频分类)。 目前引擎类型支持两种形式：python 及 inference (Paddle Inference) +**注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。 -这个 ASR client 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。 +ASR client 的输入是一个 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 ASR client的示例音频： ```bash @@ -52,8 +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://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) + 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) ``` @@ -75,8 +76,8 @@ 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://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) + 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) ``` diff --git a/demos/speech_server/conf/application.yaml b/demos/speech_server/conf/application.yaml index 2b1a0599..762f4af6 100644 --- a/demos/speech_server/conf/application.yaml +++ b/demos/speech_server/conf/application.yaml @@ -1,4 +1,4 @@ -# This is the parameter configuration file for PaddleSpeech Serving. +# This is the parameter configuration file for PaddleSpeech Offline Serving. ################################################################################# # SERVER SETTING # @@ -7,8 +7,8 @@ host: 127.0.0.1 port: 8090 # The task format in the engin_list is: _ -# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference'] - +# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference'] +protocol: 'http' engine_list: ['asr_python', 'tts_python', 'cls_python'] diff --git a/demos/streaming_tts_server/README.md b/demos/streaming_tts_server/README.md index d03b9e28..299aa3d2 100644 --- a/demos/streaming_tts_server/README.md +++ b/demos/streaming_tts_server/README.md @@ -10,7 +10,7 @@ This demo is an implementation of starting the streaming speech synthesis servic ### 1. Installation see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -It is recommended to use **paddlepaddle 2.2.1** or above. +It is recommended to use **paddlepaddle 2.2.2** or above. You can choose one way from meduim and hard to install paddlespeech. @@ -29,6 +29,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`. - When the voc model is mb_melgan, when voc_pad=14, the synthetic audio for streaming inference is consistent with the non-streaming synthetic audio; the minimum voc_pad can be set to 7, and the synthetic audio has no abnormal hearing. If the voc_pad is less than 7, the synthetic audio sounds abnormal. - When the voc model is hifigan, when voc_pad=20, the streaming inference synthetic audio is consistent with the non-streaming synthetic audio; when voc_pad=14, the synthetic audio has no abnormal hearing. - Inference speed: mb_melgan > hifigan; Audio quality: mb_melgan < hifigan +- **Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address. + ### 3. Streaming speech synthesis server and client using http protocol @@ -120,6 +122,7 @@ The configuration file can be found in `conf/tts_online_application.yaml`. - `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0 - `output`: Output wave filepath. Default: None, which means not to save the audio to the local. - `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**. + - `spk_id, speed, volume, sample_rate` do not take effect in streaming speech synthesis service temporarily. Output: ```bash @@ -254,6 +257,7 @@ The configuration file can be found in `conf/tts_online_application.yaml`. - `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0 - `output`: Output wave filepath. Default: None, which means not to save the audio to the local. - `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**. + - `spk_id, speed, volume, sample_rate` do not take effect in streaming speech synthesis service temporarily. Output: diff --git a/demos/streaming_tts_server/README_cn.md b/demos/streaming_tts_server/README_cn.md index e40de11b..bb159503 100644 --- a/demos/streaming_tts_server/README_cn.md +++ b/demos/streaming_tts_server/README_cn.md @@ -10,25 +10,27 @@ ### 1. 安装 请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -推荐使用 **paddlepaddle 2.2.1** 或以上版本。 +推荐使用 **paddlepaddle 2.2.2** 或以上版本。 你可以从 medium，hard 两种方式中选择一种方式安装 PaddleSpeech。 ### 2. 准备配置文件 配置文件可参见 `conf/tts_online_application.yaml` 。 -- `protocol`表示该流式TTS服务使用的网络协议，目前支持 **http 和 websocket** 两种。 -- `engine_list`表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。 - - 该demo主要介绍流式语音合成服务，因此语音任务应设置为tts。 - - 目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用onnxruntime进行推理的引擎。其中，online-onnx的推理速度更快。 -- 流式TTS引擎的AM模型支持：**fastspeech2 以及fastspeech2_cnndecoder**; Voc 模型支持：**hifigan, mb_melgan** -- 流式am推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`am_block`表示chunk中的有效帧数，`am_pad` 表示一个chunk中am_block前后各加的帧数。am_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 - - fastspeech2不支持流式am推理，因此am_pad与am_block对它无效 - - fastspeech2_cnndecoder 支持流式推理，当am_pad=12时，流式推理合成音频与非流式合成音频一致 -- 流式voc推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`voc_block`表示chunk中的有效帧数，`voc_pad` 表示一个chunk中voc_block前后各加的帧数。voc_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 - - hifigan, mb_melgan 均支持流式voc 推理 - - 当voc模型为mb_melgan，当voc_pad=14时，流式推理合成音频与非流式合成音频一致；voc_pad最小可以设置为7，合成音频听感上没有异常，若voc_pad小于7，合成音频听感上存在异常。 - - 当voc模型为hifigan，当voc_pad=20时，流式推理合成音频与非流式合成音频一致；当voc_pad=14时，合成音频听感上没有异常。 +- `protocol` 表示该流式 TTS 服务使用的网络协议，目前支持 **http 和 websocket** 两种。 +- `engine_list` 表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。 + - 该 demo 主要介绍流式语音合成服务，因此语音任务应设置为 tts。 + - 目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用 onnxruntime 进行推理的引擎。其中，online-onnx 的推理速度更快。 +- 流式 TTS 引擎的 AM 模型支持：**fastspeech2 以及fastspeech2_cnndecoder**; Voc 模型支持：**hifigan, mb_melgan** +- 流式 am 推理中，每次会对一个 chunk 的数据进行推理以达到流式的效果。其中 `am_block` 表示 chunk 中的有效帧数，`am_pad` 表示一个 chunk 中 am_block 前后各加的帧数。am_pad 的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 + - fastspeech2 不支持流式 am 推理，因此 am_pad 与 m_block 对它无效 + - fastspeech2_cnndecoder 支持流式推理，当 am_pad=12 时，流式推理合成音频与非流式合成音频一致 +- 流式 voc 推理中，每次会对一个 chunk 的数据进行推理以达到流式的效果。其中 `voc_block` 表示chunk中的有效帧数，`voc_pad` 表示一个 chunk 中 voc_block 前后各加的帧数。voc_pad 的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 + - hifigan, mb_melgan 均支持流式 voc 推理 + - 当 voc 模型为 mb_melgan，当 voc_pad=14 时，流式推理合成音频与非流式合成音频一致；voc_pad 最小可以设置为7，合成音频听感上没有异常，若 voc_pad 小于7，合成音频听感上存在异常。 + - 当 voc 模型为 hifigan，当 voc_pad=20 时，流式推理合成音频与非流式合成音频一致；当 voc_pad=14 时，合成音频听感上没有异常。 - 推理速度：mb_melgan > hifigan; 音频质量：mb_melgan < hifigan +- **注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。 + ### 3. 使用http协议的流式语音合成服务端及客户端使用方法 #### 3.1 服务端使用方法 @@ -119,6 +121,7 @@ - `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同 - `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。 - `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。 + - `spk_id, speed, volume, sample_rate` 在流式语音合成服务中暂时不生效。 输出: @@ -254,6 +257,7 @@ - `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同 - `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。 - `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。 + - `spk_id, speed, volume, sample_rate` 在流式语音合成服务中暂时不生效。 输出: diff --git a/docs/source/released_model.md b/docs/source/released_model.md index aee44859..61a3eb26 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -6,8 +6,10 @@ ### Speech Recognition Model Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech | Example Link :-------------:| :------------:| :-----: | -----: | :-----: |:-----:| :-----: | :-----: | :-----: -[Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_fbank161_ckpt_0.2.1.model.tar.gz) | Aishell Dataset | Char-based | 491 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.0666 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) +[Ds2 Online Wenetspeech ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr0/asr0_deepspeech2_online_wenetspeech_ckpt_1.0.0a.model.tar.gz) | Wenetspeech Dataset | Char-based | 1.2 GB | 2 Conv + 5 LSTM layers | 0.152 (test\_net, w/o LM), 0.053 (aishell, w/ LM) |-| 10000 h |- +[Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_fbank161_ckpt_0.2.1.model.tar.gz) | Aishell Dataset | Char-based | 491 MB | 2 Conv + 5 LSTM layers | 0.0666 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_aishell_ckpt_0.1.1.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) +[Conformer Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz) | WenetSpeech Dataset | Char-based | 457 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.11 (test\_net) |-| 10000 h |- [Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.2.0.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.0544 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) [Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0464 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) [Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0523 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1) diff --git a/examples/wenetspeech/asr0/RESULTS.md b/examples/wenetspeech/asr0/RESULTS.md new file mode 100644 index 00000000..17c0b9e5 --- /dev/null +++ b/examples/wenetspeech/asr0/RESULTS.md @@ -0,0 +1,7 @@ +# Wenetspeech + +## Deepspeech2 Streaming + +| Model | Number of Params | Release | Config | Test set | Valid Loss | CER | +| --- | --- | --- | --- | --- | --- | --- | +| DeepSpeech2 | 1.2G | r1.0.0a | conf/deepspeech2\_online.yaml + spec aug + fbank161 | test\_net | 13.307 | 15.02 | diff --git a/examples/wenetspeech/asr1/RESULTS.md b/examples/wenetspeech/asr1/RESULTS.md index 5c2b8143..2b03b3f2 100644 --- a/examples/wenetspeech/asr1/RESULTS.md +++ b/examples/wenetspeech/asr1/RESULTS.md @@ -1,9 +1,19 @@ # WenetSpeech +## Conformer online + +| Model | Params | Config | Augmentation| Test set | Decode method | Loss | CER | +| --- | --- | --- | --- | --- | --- | --- | --- | +| conformer | 123.47 M | conf/chunk_conformer.yaml | spec_aug | test net | attention | 9.329 | 0.1102 | +| conformer | 123.47 M | conf/chunk_conformer.yaml | spec_aug | test net | ctc_greedy_search | 9.329 | 0.1207 | +| conformer | 123.47 M | conf/chunk_conformer.yaml | spec_aug | test net | ctc_prefix_beam_search | 9.329 | 0.1203 | +| conformer | 123.47 M | conf/chunk_conformer.yaml | spec_aug | test net | attention_rescoring | 9.329 | 0.1100 | + + ## Conformer -| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER | +| Model | Params | Config | Augmentation| Test set | Decode method | Loss | CER | | --- | --- | --- | --- | --- | --- | --- | --- | | conformer | 32.52 M | conf/conformer.yaml | spec_aug | dev | attention | | | | conformer | 32.52 M | conf/conformer.yaml | spec_aug | test net | ctc_greedy_search | | | @@ -16,7 +26,7 @@ Pretrain model from http://mobvoi-speech-public.ufile.ucloud.cn/public/wenet/wenetspeech/20211025_conformer_exp.tar.gz -| Model | Params | Config | Augmentation| Test set | Decode method | Loss | WER | +| Model | Params | Config | Augmentation| Test set | Decode method | Loss | CER | | --- | --- | --- | --- | --- | --- | --- | --- | | conformer | 32.52 M | conf/conformer.yaml | spec_aug | aishell1 | attention | - | 0.048456 | | conformer | 32.52 M | conf/conformer.yaml | spec_aug | aishell1 | ctc_greedy_search | - | 0.052534 | diff --git a/paddlespeech/cli/asr/pretrained_models.py b/paddlespeech/cli/asr/pretrained_models.py index 80b04aa4..7f198ad6 100644 --- a/paddlespeech/cli/asr/pretrained_models.py +++ b/paddlespeech/cli/asr/pretrained_models.py @@ -27,6 +27,16 @@ pretrained_models = { 'ckpt_path': 'exp/conformer/checkpoints/wenetspeech', }, + "conformer_online_wenetspeech-zh-16k": { + 'url': + 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz', + 'md5': + 'b8c02632b04da34aca88459835be54a6', + 'cfg_path': + 'model.yaml', + 'ckpt_path': + 'exp/chunk_conformer/checkpoints/avg_10', + }, "conformer_online_multicn-zh-16k": { 'url': 'https://paddlespeech.bj.bcebos.com/s2t/multi_cn/asr1/asr1_chunk_conformer_multi_cn_ckpt_0.2.0.model.tar.gz', @@ -69,13 +79,13 @@ pretrained_models = { }, "deepspeech2online_wenetspeech-zh-16k": { 'url': - 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr0/WIP_asr0_deepspeech2_online_wenetspeech_ckpt_1.0.0a.model.tar.gz', + 'https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr0/asr0_deepspeech2_online_wenetspeech_ckpt_1.0.0a.model.tar.gz', 'md5': - 'b3ef6fcae8c0058c3c53375341ccb209', + 'e393d4d274af0f6967db24fc146e8074', 'cfg_path': 'model.yaml', 'ckpt_path': - 'exp/deepspeech2_online/checkpoints/avg_3', + 'exp/deepspeech2_online/checkpoints/avg_10', 'lm_url': 'https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm', 'lm_md5': diff --git a/paddlespeech/cli/base_commands.py b/paddlespeech/cli/base_commands.py index 97d5cd7f..0a26b120 100644 --- a/paddlespeech/cli/base_commands.py +++ b/paddlespeech/cli/base_commands.py @@ -47,3 +47,29 @@ class HelpCommand: print(msg) return True + + +@cli_register( + name='paddlespeech.version', + description='Show version and commit id of current package.') +class VersionCommand: + def execute(self, argv: List[str]) -> bool: + try: + from .. import __version__ + version = __version__ + except ImportError: + version = 'Not an official release' + + try: + from .. import __commit__ + commit_id = __commit__ + except ImportError: + commit_id = 'Not found' + + msg = 'Package Version:\n' + msg += ' {}\n\n'.format(version) + msg += 'Commit ID:\n' + msg += ' {}\n\n'.format(commit_id) + + print(msg) + return True diff --git a/paddlespeech/server/README.md b/paddlespeech/server/README.md index 98ec1e28..f3dc9224 100644 --- a/paddlespeech/server/README.md +++ b/paddlespeech/server/README.md @@ -10,7 +10,9 @@ paddlespeech_server help ``` ### Start the server - First set the service-related configuration parameters, similar to `./conf/application.yaml`. Set `engine_list`, which represents the speech tasks included in the service to be started + First set the service-related configuration parameters, similar to `./conf/application.yaml`. Set `engine_list`, which represents the speech tasks included in the service to be started. + **Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address. + Then start the service: ```bash paddlespeech_server start --config_file ./conf/application.yaml diff --git a/paddlespeech/server/README_cn.md b/paddlespeech/server/README_cn.md index a974d40f..4bd4d873 100644 --- a/paddlespeech/server/README_cn.md +++ b/paddlespeech/server/README_cn.md @@ -11,6 +11,7 @@ ``` ### 启动服务 首先设置服务相关配置文件，类似于 `./conf/application.yaml`，设置 `engine_list`，该值表示即将启动的服务中包含的语音任务。 + **注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。 然后启动服务： ```bash paddlespeech_server start --config_file ./conf/application.yaml diff --git a/setup.py b/setup.py index 912fdd6d..252c1918 100644 --- a/setup.py +++ b/setup.py @@ -27,7 +27,7 @@ from setuptools.command.install import install HERE = Path(os.path.abspath(os.path.dirname(__file__))) -VERSION = '1.0.0a' +VERSION = '0.0.0' base = [ "editdistance", diff --git a/tests/unit/cli/test_cli.sh b/tests/unit/cli/test_cli.sh index bdf05524..e1f1853f 100755 --- a/tests/unit/cli/test_cli.sh +++ b/tests/unit/cli/test_cli.sh @@ -14,6 +14,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee paddlespeech asr --input ./zh.wav paddlespeech asr --model conformer_aishell --input ./zh.wav paddlespeech asr --model conformer_online_aishell --input ./zh.wav +paddlespeech asr --model conformer_online_wenetspeech --input ./zh.wav paddlespeech asr --model conformer_online_multicn --input ./zh.wav paddlespeech asr --model transformer_librispeech --lang en --input ./en.wav paddlespeech asr --model deepspeech2offline_aishell --input ./zh.wav