diff --git a/.flake8 b/.flake8 index 6b50de7ed..ae15ad2be 100644 --- a/.flake8 +++ b/.flake8 @@ -33,7 +33,7 @@ filename = # Specify a list of codes to ignore. ignore = W503 - E252,E262,E127,E265,E126,E266,E241,E261,E128,E125 + E252,E262,E127,E265,E126,E266,E241,E261,E128,E125,E129 W291,W293,W605 E203,E305,E402,E501,E721,E741,F403,F405,F821,F841,F999,W503,W504,C408,E302,W291,E303, # shebang has extra meaning in fbcode lints, so I think it's not worth trying diff --git a/README.md b/README.md index 72db64b7d..79b86e9ff 100644 --- a/README.md +++ b/README.md @@ -183,12 +183,12 @@ Via the easy-to-use, efficient, flexible and scalable implementation, our vision ## Installation -We strongly recommend our users to install PaddleSpeech in **Linux** with *python>=3.7* and *paddlepaddle>=2.3.1*. +We strongly recommend our users to install PaddleSpeech in **Linux** with *python>=3.7* and *paddlepaddle>=2.4rc*. ### **Dependency Introduction** + gcc >= 4.8.5 -+ paddlepaddle >= 2.3.1 ++ paddlepaddle >= 2.4rc + python >= 3.7 + OS support: Linux(recommend), Windows, Mac OSX @@ -197,6 +197,13 @@ PaddleSpeech depends on paddlepaddle. For installation, please refer to the offi ```bash pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple ``` +You can also specify the version of paddlepaddle or install the develop version. +```bash +# install 2.3.1 version. Note, 2.3.1 is just an example, please follow the minimum dependency of paddlepaddle for your selection +pip install paddlepaddle==2.3.1 -i https://mirror.baidu.com/pypi/simple +# install develop version +pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html +``` There are two quick installation methods for PaddleSpeech, one is pip installation, and the other is source code compilation (recommended). ### pip install diff --git a/README_cn.md b/README_cn.md index 725f7eda1..3d60882b2 100644 --- a/README_cn.md +++ b/README_cn.md @@ -215,7 +215,7 @@ ### 相关依赖 + gcc >= 4.8.5 -+ paddlepaddle >= 2.3.1 ++ paddlepaddle >= 2.4rc + python >= 3.7 + linux(推荐), mac, windows @@ -224,7 +224,13 @@ PaddleSpeech 依赖于 paddlepaddle，安装可以参考[ paddlepaddle 官网](h ```shell pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple ``` - +你也可以安装指定版本的paddlepaddle，或者安装 develop 版本。 +```bash +# 安装2.3.1版本. 注意：2.3.1只是一个示例，请按照对paddlepaddle的最小依赖进行选择。 +pip install paddlepaddle==2.3.1 -i https://mirror.baidu.com/pypi/simple +# 安装 develop 版本 +pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html +``` PaddleSpeech 快速安装方式有两种，一种是 pip 安装，一种是源码编译（推荐）。 ### pip 安装 diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index e400f7e74..7e7d4b2c5 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -13,7 +13,7 @@ For service interface definition, please check: ### 1. Installation see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -It is recommended to use **paddlepaddle 2.3.1** or above. +It is recommended to use **paddlepaddle 2.4rc** or above. You can choose one way from easy, meduim and hard to install paddlespeech. diff --git a/demos/speech_server/README_cn.md b/demos/speech_server/README_cn.md index 628468c83..594928281 100644 --- a/demos/speech_server/README_cn.md +++ b/demos/speech_server/README_cn.md @@ -14,7 +14,7 @@ ### 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 2.3.1** 或以上版本。 +推荐使用 **paddlepaddle 2.4rc** 或以上版本。 你可以从简单，中等，困难 几种方式中选择一种方式安装 PaddleSpeech。 diff --git a/demos/streaming_asr_server/README.md b/demos/streaming_asr_server/README.md index a97486757..5eef82866 100644 --- a/demos/streaming_asr_server/README.md +++ b/demos/streaming_asr_server/README.md @@ -14,7 +14,7 @@ Streaming ASR server only support `websocket` protocol, and doesn't support `htt ### 1. Installation see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -It is recommended to use **paddlepaddle 2.3.1** or above. +It is recommended to use **paddlepaddle 2.4rc** or above. You can choose one way from easy, meduim and hard to install paddlespeech. diff --git a/demos/streaming_asr_server/README_cn.md b/demos/streaming_asr_server/README_cn.md index 267367729..1902a2fa9 100644 --- a/demos/streaming_asr_server/README_cn.md +++ b/demos/streaming_asr_server/README_cn.md @@ -14,7 +14,7 @@ ### 1. 安装 安装 PaddleSpeech 的详细过程请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md)。 -推荐使用 **paddlepaddle 2.3.1** 或以上版本。 +推荐使用 **paddlepaddle 2.4rc** 或以上版本。 你可以从简单，中等，困难 几种方式中选择一种方式安装 PaddleSpeech。 diff --git a/demos/streaming_tts_server/README.md b/demos/streaming_tts_server/README.md index 15448a46f..ca5d6f1f8 100644 --- a/demos/streaming_tts_server/README.md +++ b/demos/streaming_tts_server/README.md @@ -13,7 +13,7 @@ For service interface definition, please check: ### 1. Installation see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). -It is recommended to use **paddlepaddle 2.3.1** or above. +It is recommended to use **paddlepaddle 2.4rc** or above. You can choose one way from easy, meduim and hard to install paddlespeech. diff --git a/demos/streaming_tts_server/README_cn.md b/demos/streaming_tts_server/README_cn.md index b99155bca..125f37033 100644 --- a/demos/streaming_tts_server/README_cn.md +++ b/demos/streaming_tts_server/README_cn.md @@ -12,7 +12,7 @@ ### 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 2.3.1** 或以上版本。 +推荐使用 **paddlepaddle 2.4rc** 或以上版本。 你可以从简单，中等，困难 几种方式中选择一种方式安装 PaddleSpeech。 diff --git a/docker/ubuntu16-gpu/Dockerfile b/docker/ubuntu16-gpu/Dockerfile index f275471ee..a8c11e37b 100644 --- a/docker/ubuntu16-gpu/Dockerfile +++ b/docker/ubuntu16-gpu/Dockerfile @@ -62,7 +62,7 @@ RUN mkdir -p ~/.pip && echo "[global]" > ~/.pip/pip.conf && \ echo "index-url=https://mirror.baidu.com/pypi/simple" >> ~/.pip/pip.conf && \ echo "trusted-host=mirror.baidu.com" >> ~/.pip/pip.conf && \ python3 -m pip install --upgrade pip && \ - pip install paddlepaddle-gpu==2.3.1.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html && \ + pip install paddlepaddle-gpu==2.4.0rc0.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html && \ rm -rf ~/.cache/pip RUN git clone https://github.com/PaddlePaddle/PaddleSpeech.git && cd PaddleSpeech && \ diff --git a/docs/source/install.md b/docs/source/install.md index 6a9ff3bc8..1e6c1c48b 100644 --- a/docs/source/install.md +++ b/docs/source/install.md @@ -61,6 +61,13 @@ Then you can use the following commands: pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple ``` +You can also specify the version of paddlepaddle or install the develop version. +```bash +# install 2.3.1 version. Note, 2.3.1 is just an example, please follow the minimum dependency of paddlepaddle for your selection +pip install paddlepaddle==2.3.1 -i https://mirror.baidu.com/pypi/simple +# install develop version +pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html +``` > If you encounter problem with downloading **nltk_data** while using paddlespeech, it maybe due to your poor network, we suggest you download the [nltk_data](https://paddlespeech.bj.bcebos.com/Parakeet/tools/nltk_data.tar.gz) provided by us, and extract it to your `${HOME}`. > If you fail to install paddlespeech-ctcdecoders, you only can not use deepspeech2 model inference. For other models, it doesn't matter. @@ -117,9 +124,14 @@ conda install -y -c gcc_linux-64=8.4.0 gxx_linux-64=8.4.0 ``` (Hip: Do not use the last script if you want to install by **Hard** way): ### Install PaddlePaddle -You can choose the `PaddlePaddle` version based on your system. For example, for CUDA 10.2, CuDNN7.5 install paddlepaddle-gpu 2.3.1: +You can choose the `PaddlePaddle` version based on your system. For example, for CUDA 10.2, CuDNN7.6 install paddlepaddle-gpu 2.4rc: +```bash +# Note, 2.4rc is just an example, please follow the minimum dependency of paddlepaddle for your selection +python3 -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://mirror.baidu.com/pypi/simple +``` +You can also install the develop version of paddlepaddle. For example, for CUDA 10.2, CuDNN7.6 install paddlepaddle-gpu develop: ```bash -python3 -m pip install paddlepaddle-gpu==2.3.1 -i https://mirror.baidu.com/pypi/simple +python3 -m pip install paddlepaddle-gpu==0.0.0.post102 -f https://www.paddlepaddle.org.cn/whl/linux/gpu/develop.html ``` ### Install PaddleSpeech You can install `paddlespeech` by the following command，then you can use the `ready-made` examples in `paddlespeech` : @@ -180,9 +192,14 @@ Some users may fail to install `kaldiio` due to the default download source, you ```bash pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple ``` -Make sure you have GPU and the paddlepaddle version is right. For example, for CUDA 10.2, CuDNN7.5 install paddle 2.3.1: +Make sure you have GPU and the paddlepaddle version is right. For example, for CUDA 10.2, CuDNN7.6 install paddle 2.4rc: +```bash +# Note, 2.4rc is just an example, please follow the minimum dependency of paddlepaddle for your selection +python3 -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://mirror.baidu.com/pypi/simple +``` +You can also install the develop version of paddlepaddle. For example, for CUDA 10.2, CuDNN7.6 install paddlepaddle-gpu develop: ```bash -python3 -m pip install paddlepaddle-gpu==2.3.1 -i https://mirror.baidu.com/pypi/simple +python3 -m pip install paddlepaddle-gpu==0.0.0.post102 -f https://www.paddlepaddle.org.cn/whl/linux/gpu/develop.html ``` ### Install PaddleSpeech in Developing Mode ```bash diff --git a/docs/source/install_cn.md b/docs/source/install_cn.md index 9f49ebad6..ebc0cf7a2 100644 --- a/docs/source/install_cn.md +++ b/docs/source/install_cn.md @@ -56,7 +56,14 @@ pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple 然后你可以使用如下命令： ```bash pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple -pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple +pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple +``` +你也可以安装指定版本的paddlepaddle，或者安装 develop 版本。 +```bash +# 安装2.3.1版本. 注意：2.3.1只是一个示例，请按照对paddlepaddle的最小依赖进行选择。 +pip install paddlepaddle==2.3.1 -i https://mirror.baidu.com/pypi/simple +# 安装 develop 版本 +pip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html ``` > 如果您在使用 paddlespeech 的过程中遇到关于下载 **nltk_data** 的问题，可能是您的网络不佳，我们建议您下载我们提供的 [nltk_data](https://paddlespeech.bj.bcebos.com/Parakeet/tools/nltk_data.tar.gz) 并解压缩到您的 `${HOME}` 目录下。 @@ -111,9 +118,14 @@ conda install -y -c gcc_linux-64=8.4.0 gxx_linux-64=8.4.0 ``` （提示： 如果你想使用**困难**方式完成安装，请不要使用最后一条命令） ### 安装 PaddlePaddle -你可以根据系统配置选择 PaddlePaddle 版本，例如系统使用 CUDA 10.2， CuDNN7.5 ，你可以安装 paddlepaddle-gpu 2.3.1： +你可以根据系统配置选择 PaddlePaddle 版本，例如系统使用 CUDA 10.2， CuDNN7.6，你可以安装 paddlepaddle-gpu 2.4rc： +```bash +# 注意：2.4rc 只是一个示例，请按照对paddlepaddle的最小依赖进行选择。 +python3 -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://mirror.baidu.com/pypi/simple +``` +你也可以安装 develop 版本的PaddlePaddle. 例如系统使用 CUDA 10.2， CuDNN7.6 ，你可以安装 paddlepaddle-gpu develop: ```bash -python3 -m pip install paddlepaddle-gpu==2.3.1 -i https://mirror.baidu.com/pypi/simple +python3 -m pip install paddlepaddle-gpu==0.0.0.post102 -f https://www.paddlepaddle.org.cn/whl/linux/gpu/develop.html ``` ### 安装 PaddleSpeech 最后安装 `paddlespeech`，这样你就可以使用 `paddlespeech` 中已有的 examples： @@ -168,13 +180,18 @@ conda activate tools/venv conda install -y -c conda-forge sox libsndfile swig bzip2 libflac bc ``` ### 安装 PaddlePaddle -请确认你系统是否有 GPU，并且使用了正确版本的 paddlepaddle。例如系统使用 CUDA 10.2, CuDNN7.5 ，你可以安装 paddlepaddle-gpu 2.3.1： +请确认你系统是否有 GPU，并且使用了正确版本的 paddlepaddle。例如系统使用 CUDA 10.2, CuDNN7.6 ，你可以安装 paddlepaddle-gpu 2.4rc： +```bash +python3 -m pip install paddlepaddle-gpu==2.4.0rc0 -i https://mirror.baidu.com/pypi/simple +``` +你也可以安装 develop 版本的PaddlePaddle. 例如系统使用 CUDA 10.2， CuDNN7.6 ，你可以安装 paddlepaddle-gpu develop: ```bash -python3 -m pip install paddlepaddle-gpu==2.3.1 -i https://mirror.baidu.com/pypi/simple +python3 -m pip install paddlepaddle-gpu==0.0.0.post102 -f https://www.paddlepaddle.org.cn/whl/linux/gpu/develop.html ``` ### 用开发者模式安装 PaddleSpeech 部分用户系统由于默认源的问题，安装中会出现 kaldiio 安转出错的问题，建议首先安装 pytest-runner: ```bash +# 注意：2.4rc 只是一个示例，请按照对paddlepaddle的最小依赖进行选择。 pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple ``` 然后安装 PaddleSpeech： diff --git a/docs/source/released_model.md b/docs/source/released_model.md index bdac2c5bb..a2456f1fe 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -9,7 +9,7 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | [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) | onnx/inference/python | [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_offline_aishell_ckpt_1.0.1.model.tar.gz)| Aishell Dataset | Char-based | 1.4 GB | 2 Conv + 5 bidirectional LSTM layers| 0.0554 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) | inference/python | [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) 0.1879 (test\_meeting) |-| 10000 h |- | python | -[Conformer U2PP Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.1.1.model.tar.gz) | WenetSpeech Dataset | Char-based | 476 MB | Encoder:Conformer, Decoder:BiTransformer, Decoding method: Attention rescoring| 0.047198 (aishell test\_-1) 0.059212 (aishell test\_16) |-| 10000 h |- | python | +[Conformer U2PP Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_u2pp_wenetspeech_ckpt_1.1.4.model.tar.gz) | WenetSpeech Dataset | Char-based | 476 MB | Encoder:Conformer, Decoder:BiTransformer, Decoding method: Attention rescoring| 0.047198 (aishell test\_-1) 0.059212 (aishell test\_16) |-| 10000 h |- | python | [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) | python | [Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_1.0.1.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0460 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) | python | [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) | python | diff --git a/examples/librispeech/README.md b/examples/librispeech/README.md index 74441fd09..9fcbde97a 100644 --- a/examples/librispeech/README.md +++ b/examples/librispeech/README.md @@ -3,7 +3,7 @@ * asr0 - deepspeech2 Streaming/Non-Streaming * asr1 - transformer/conformer Streaming/Non-Streaming * asr2 - transformer/conformer Streaming/Non-Streaming with Kaldi feature - +* asr3 - wav2vecASR, ASR model with pre-trained wav2vec2 and CTC ## Data | Data Subset | Duration in Seconds | diff --git a/examples/librispeech/asr3/README.md b/examples/librispeech/asr3/README.md new file mode 100644 index 000000000..f99beb338 --- /dev/null +++ b/examples/librispeech/asr3/README.md @@ -0,0 +1,197 @@ +# Wav2vec2ASR with Librispeech +This example contains code used to finetune [wav2vec2.0](https://https://arxiv.org/pdf/2006.11477.pdf) model with [Librispeech dataset](http://www.openslr.org/resources/12) +## Overview +All the scripts you need are in `run.sh`. There are several stages in `run.sh`, and each stage has its function. +| Stage | Function | +|:---- |:----------------------------------------------------------- | +| 0 | Process data. It includes:
(1) Download the dataset
(2) Calculate the CMVN of the train dataset
(3) Get the vocabulary file
(4) Get the manifest files of the train, development and test dataset
(5) Download the pretrained wav2vec2 model | +| 1 | Train the model | +| 2 | Get the final model by averaging the top-k models, set k = 1 means to choose the best model | +| 3 | Test the final model performance | +| 4 | Infer the single audio file | + + +You can choose to run a range of stages by setting `stage` and `stop_stage `. + +For example, if you want to execute the code in stage 2 and stage 3, you can run this script: +```bash +bash run.sh --stage 2 --stop_stage 3 +``` +Or you can set `stage` equal to `stop-stage` to only run one stage. +For example, if you only want to run `stage 0`, you can use the script below: +```bash +bash run.sh --stage 0 --stop_stage 0 +``` +The document below will describe the scripts in `run.sh` in detail. +## The Environment Variables +The path.sh contains the environment variables. +```bash +. ./path.sh +. ./cmd.sh +``` +This script needs to be run first. And another script is also needed: +```bash +source ${MAIN_ROOT}/utils/parse_options.sh +``` +It will support the way of using `--variable value` in the shell scripts. +## The Local Variables +Some local variables are set in `run.sh`. +`gpus` denotes the GPU number you want to use. If you set `gpus=`, it means you only use CPU. +`stage` denotes the number of stages you want to start from in the experiments. +`stop stage` denotes the number of the stage you want to end at in the experiments. +`conf_path` denotes the config path of the model. +`avg_num` denotes the number K of top-K models you want to average to get the final model. +`audio file` denotes the file path of the single file you want to infer in stage 5 +`ckpt` denotes the checkpoint prefix of the model, e.g. "wav2vec2ASR" + +You can set the local variables (except `ckpt`) when you use `run.sh` + +For example, you can set the `gpus` and `avg_num` when you use the command line: +```bash +bash run.sh --gpus 0,1 --avg_num 20 +``` +## Stage 0: Data Processing +To use this example, you need to process data firstly and you can use stage 0 in `run.sh` to do this. The code is shown below: +```bash + if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then + # prepare data + bash ./local/data.sh || exit -1 + fi +``` +Stage 0 is for processing the data. + +If you only want to process the data. You can run +```bash +bash run.sh --stage 0 --stop_stage 0 +``` +You can also just run these scripts in your command line. +```bash +. ./path.sh +. ./cmd.sh +bash ./local/data.sh +``` +After processing the data, the `data` directory will look like this: +```bash +data/ +|-- dev.meta +|-- lang_char +| `-- bpe_unigram_5000.model +| `-- bpe_unigram_5000.vocab +| `-- vocab.txt +|-- manifest.dev +|-- manifest.dev.raw +|-- manifest.test +|-- manifest.test.raw +|-- manifest.train +|-- manifest.train.raw +|-- mean_std.json +|-- test.meta +`-- train.meta +``` + +Stage 0 also downloads the pre-trained [wav2vec2](https://paddlespeech.bj.bcebos.com/wav2vec/wav2vec2-large-960h-lv60-self.pdparams) model. +```bash +mkdir -p exp/wav2vec2 +wget -P exp/wav2vec2 https://paddlespeech.bj.bcebos.com/wav2vec/wav2vec2-large-960h-lv60-self.pdparams +``` +## Stage 1: Model Training +If you want to train the model. you can use stage 1 in `run.sh`. The code is shown below. +```bash +if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then + # train model, all `ckpt` under `exp` dir + CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} + fi +``` +If you want to train the model, you can use the script below to execute stage 0 and stage 1: +```bash +bash run.sh --stage 0 --stop_stage 1 +``` +or you can run these scripts in the command line (only use CPU). +```bash +. ./path.sh +. ./cmd.sh +bash ./local/data.sh +CUDA_VISIBLE_DEVICES= ./local/train.sh conf/wav2vec2ASR.yaml wav2vec2ASR +``` +## Stage 2: Top-k Models Averaging +After training the model, we need to get the final model for testing and inference. In every epoch, the model checkpoint is saved, so we can choose the best model from them based on the validation loss or we can sort them and average the parameters of the top-k models to get the final model. We can use stage 2 to do this, and the code is shown below. Note: We only train one epoch for wav2vec2ASR, thus the `avg_num` is set to 1. +```bash + if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then + # avg n best model + avg.sh best exp/${ckpt}/checkpoints ${avg_num} + fi +``` +The `avg.sh` is in the `../../../utils/` which is define in the `path.sh`. +If you want to get the final model, you can use the script below to execute stage 0, stage 1, and stage 2: +```bash +bash run.sh --stage 0 --stop_stage 2 +``` +or you can run these scripts in the command line (only use CPU). + +```bash +. ./path.sh +. ./cmd.sh +bash ./local/data.sh +CUDA_VISIBLE_DEVICES= ./local/train.sh conf/wav2vec2ASR.yaml wav2vec2ASR +avg.sh best exp/wav2vec2ASR/checkpoints 1 +``` +## Stage 3: Model Testing +The test stage is to evaluate the model performance. The code of test stage is shown below: +```bash + if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then + # test ckpt avg_n + CUDA_VISIBLE_DEVICES=0 ./local/test.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1 + fi +``` +If you want to train a model and test it, you can use the script below to execute stage 0, stage 1, stage 2, and stage 3 : +```bash +bash run.sh --stage 0 --stop_stage 3 +``` +or you can run these scripts in the command line (only use CPU). +```bash +. ./path.sh +. ./cmd.sh +bash ./local/data.sh +CUDA_VISIBLE_DEVICES= ./local/train.sh conf/wav2vec2ASR.yaml wav2vec2ASR +avg.sh best exp/wav2vec2ASR/checkpoints 1 +CUDA_VISIBLE_DEVICES= ./local/test.sh conf/wav2vec2ASR.yaml conf/tuning/decode.yaml exp/wav2vec2ASR/checkpoints/avg_1 +``` +## Pretrained Model +You can get the pretrained wav2vec2ASR from [this](../../../docs/source/released_model.md). + +using the `tar` scripts to unpack the model and then you can use the script to test the model. + +For example: +```bash +wget https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr3/wav2vec2ASR-large-960h-librispeech_ckpt_1.3.0.model.tar.gz +tar xzvf wav2vec2ASR-large-960h-librispeech_ckpt_1.3.0.model.tar.gz +source path.sh +# If you have process the data and get the manifest file， you can skip the following 2 steps +bash local/data.sh --stage -1 --stop_stage -1 +bash local/data.sh --stage 2 --stop_stage 2 +CUDA_VISIBLE_DEVICES= ./local/test.sh conf/wav2vec2ASR.yaml conf/tuning/decode.yaml exp/wav2vec2ASR/checkpoints/avg_1 +``` +The performance of the released models are shown in [here](./RESULTS.md). + + +## Stage 4: Single Audio File Inference +In some situations, you want to use the trained model to do the inference for the single audio file. You can use stage 5. The code is shown below +```bash + if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then + # test a single .wav file + CUDA_VISIBLE_DEVICES=0 ./local/test_wav.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} ${audio_file} || exit -1 + fi +``` +you can train the model by yourself using ```bash run.sh --stage 0 --stop_stage 3```, or you can download the pretrained model through the script below: +```bash +wget https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr3/wav2vec2ASR-large-960h-librispeech_ckpt_1.3.0.model.tar.gz +tar xzvf wav2vec2ASR-large-960h-librispeech_ckpt_1.3.0.model.tar.gz +``` +You can download the audio demo: +```bash +wget -nc https://paddlespeech.bj.bcebos.com/datasets/single_wav/en/demo_002_en.wav -P data/ +``` +You need to prepare an audio file or use the audio demo above, please confirm the sample rate of the audio is 16K. You can get the result of the audio demo by running the script below. +```bash +CUDA_VISIBLE_DEVICES= ./local/test_wav.sh conf/wav2vec2ASR.yaml conf/tuning/decode.yaml exp/wav2vec2ASR/checkpoints/avg_1 data/demo_002_en.wav +``` diff --git a/examples/librispeech/asr3/RESULTS.md b/examples/librispeech/asr3/RESULTS.md new file mode 100644 index 000000000..1c5626d9e --- /dev/null +++ b/examples/librispeech/asr3/RESULTS.md @@ -0,0 +1,8 @@ +# LibriSpeech + +## Wav2VecASR +train: Epoch 1, 1*V100-32G, batchsize:10 + +| Model | Params | Config | Augmentation| Test set | Decode method | WER | +| --- | --- | --- | --- | --- | --- | --- | +| wav2vec2ASR | 302.86 M | conf/wav2vec2ASR.yaml | spec_aug | test-clean | greedy search | 0.018887 | diff --git a/examples/librispeech/asr3/cmd.sh b/examples/librispeech/asr3/cmd.sh new file mode 100644 index 000000000..7b70ef5e0 --- /dev/null +++ b/examples/librispeech/asr3/cmd.sh @@ -0,0 +1,89 @@ +# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ====== +# Usage: .pl [options] JOB=1: +# e.g. +# run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB +# +# Options: +# --time