From e83292715fdf3e629f006ad99a177754265e82d4 Mon Sep 17 00:00:00 2001 From: hnluo Date: Mon, 26 Jun 2023 11:51:19 +0800 Subject: [PATCH 1/4] fix english hotwords bug --- funasr/bin/asr_infer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py index e12dbb544..a537a73fe 100644 --- a/funasr/bin/asr_infer.py +++ b/funasr/bin/asr_infer.py @@ -609,7 +609,7 @@ class Speech2TextParaformer: hotword_str_list = [] for hw in hotword_list_or_file.strip().split(): hotword_str_list.append(hw) - hw_list = hw + hw_list = hw.strip().split() if seg_dict is not None: hw_list = seg_tokenize(hw_list, seg_dict) hotword_list.append(self.converter.tokens2ids(hw_list)) From 1bc89cab1b001b4e0360c1f7d2507e0df5ac092d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= Date: Mon, 26 Jun 2023 14:20:51 +0800 Subject: [PATCH 2/4] v0.6.3 --- funasr/version.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/funasr/version.txt b/funasr/version.txt index b61604874..844f6a91a 100644 --- a/funasr/version.txt +++ b/funasr/version.txt @@ -1 +1 @@ -0.6.2 +0.6.3 From aa031509a7a7fcf8177e4790ca174768b55cb7ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= Date: Mon, 26 Jun 2023 14:52:08 +0800 Subject: [PATCH 3/4] Usage --- README.md | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 57ca1a252..8368b3bc7 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ [**News**](https://github.com/alibaba-damo-academy/FunASR#whats-new) | [**Highlights**](#highlights) | [**Installation**](#installation) -| [**Docs**](https://alibaba-damo-academy.github.io/FunASR/en/index.html) +| [**Usage**](#usage) | [**Papers**](https://github.com/alibaba-damo-academy/FunASR#citations) | [**Runtime**](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime) | [**Model Zoo**](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md) @@ -44,22 +44,68 @@ Or install from source code ``` sh git clone https://github.com/alibaba/FunASR.git && cd FunASR -pip install -e ./ +pip3 install -e ./ # For the users in China, you could install with the command: -# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple +# pip3 install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple ``` If you want to use the pretrained models in ModelScope, you should install the modelscope: ```shell -pip install -U modelscope +pip3 install -U modelscope # For the users in China, you could install with the command: -# pip install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple +# pip3 install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple ``` For more details, please ref to [installation](https://alibaba-damo-academy.github.io/FunASR/en/installation/installation.html) +## Usage +You could use FunASR by: + +- egs +- egs_modelscope +- runtime + +### egs +If you want to train the model from scratch, you could use funasr directly by recipe, as the following: +```shell +cd egs/aishell/paraformer +. ./run.sh --CUDA_VISIBLE_DEVICES="0,1" --gpu_num=2 +``` +More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html) + +### egs_modelscope +If you want to infer or finetune pretraining models from modelscope, you could use funasr by modelscope pipeline, as the following: + +```python +from modelscope.pipelines import pipeline +from modelscope.utils.constant import Tasks + +inference_pipeline = pipeline( + task=Tasks.auto_speech_recognition, + model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch', +) + +rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav') +print(rec_result) +# {'text': '欢迎大家来体验达摩院推出的语音识别模型'} +``` +More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/modelscope_pipeline/quick_start.html) + +### runtime + +An example with websocket: +For the server: +```shell +python wss_srv_asr.py --port 10095 +``` +For the client: +```shell +python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "5,10,5" +#python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode 2pass --chunk_size "8,8,4" --audio_in "./data/wav.scp" --output_dir "./results" +``` +More examples could be found in [docs](https://alibaba-damo-academy.github.io/FunASR/en/runtime/websocket_python.html#id2) ## Contact If you have any questions about FunASR, please contact us by From 364113a967764b094933ed1a24be6bc4d981b0f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= Date: Mon, 26 Jun 2023 15:38:32 +0800 Subject: [PATCH 4/4] leaderboardIO --- docs/benchmark/benchmark_pipeline_cer.md | 2 +- docs/index.rst | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/benchmark/benchmark_pipeline_cer.md b/docs/benchmark/benchmark_pipeline_cer.md index 9f42c9533..97776a6ae 100644 --- a/docs/benchmark/benchmark_pipeline_cer.md +++ b/docs/benchmark/benchmark_pipeline_cer.md @@ -1,4 +1,4 @@ -# Benchmark (ModeScope Pipeline) +# Leaderboard IO ## Configuration diff --git a/docs/index.rst b/docs/index.rst index cb98f3573..87e3a2540 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -77,11 +77,12 @@ Overview .. toctree:: :maxdepth: 1 - :caption: Benchmark and Leadboard + :caption: Benchmark and Leaderboard ./benchmark/benchmark_onnx.md ./benchmark/benchmark_onnx_cpp.md ./benchmark/benchmark_libtorch.md + ./benchmark/benchmark_pipeline_cer.md .. toctree::