From a05e753d11d9c36983ec4e58c421dbcf86d1dcd4 Mon Sep 17 00:00:00 2001 From: Xian Shi <40013335+R1ckShi@users.noreply.github.com> Date: 星期二, 17 十月 2023 16:47:27 +0800 Subject: [PATCH] Merge branch 'main' into dev_onnx --- egs_modelscope/asr/TEMPLATE/README.md | 39 +++++++++++++++++++++++++++++++++++++++ 1 files changed, 39 insertions(+), 0 deletions(-) diff --git a/egs_modelscope/asr/TEMPLATE/README.md b/egs_modelscope/asr/TEMPLATE/README.md index bd0e6a9..ac73950 100644 --- a/egs_modelscope/asr/TEMPLATE/README.md +++ b/egs_modelscope/asr/TEMPLATE/README.md @@ -68,6 +68,23 @@ ``` Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/241) +#### [Paraformer-contextual Model](https://www.modelscope.cn/models/damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404/summary) +```python +from modelscope.pipelines import pipeline +from modelscope.utils.constant import Tasks + +param_dict = dict() +# param_dict['hotword'] = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/hotword.txt" +param_dict['hotword']="閭撻儊鏉� 鐜嬮鏄� 鐜嬫檾鍚�" +inference_pipeline = pipeline( + task=Tasks.auto_speech_recognition, + model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", + param_dict=param_dict) + +rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_hotword.wav') +print(rec_result) +``` + #### [UniASR Model](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary) There are three decoding mode for UniASR model(`fast`銆乣normal`銆乣offline`), for more model details, please refer to [docs](https://www.modelscope.cn/models/damo/speech_UniASR_asr_2pass-zh-cn-8k-common-vocab3445-pytorch-online/summary) ```python @@ -82,6 +99,28 @@ ``` The decoding mode of `fast` and `normal` is fake streaming, which could be used for evaluating of recognition accuracy. Full code of demo, please ref to [demo](https://github.com/alibaba-damo-academy/FunASR/discussions/151) + +#### [Paraformer-Spk](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary) +This model allows user to get recognition results which contain speaker info of each sentence. Refer to [CAM++](https://modelscope.cn/models/damo/speech_campplus_speaker-diarization_common/summary) for detailed information about speaker diarization model. +```python +from modelscope.pipelines import pipeline +from modelscope.utils.constant import Tasks + +if __name__ == '__main__': + audio_in = 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_speaker_demo.wav' + output_dir = "./results" + inference_pipeline = pipeline( + task=Tasks.auto_speech_recognition, + model='damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn', + model_revision='v0.0.2', + vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch', + punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large', + output_dir=output_dir, + ) + rec_result = inference_pipeline(audio_in=audio_in, batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000) + print(rec_result) +``` + #### [RNN-T-online model]() Undo -- Gitblit v1.9.1