search

modelscope / FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
https://www.funasr.com
Other
4.62k stars 514 forks source link

KeyError: 'speaker-diarization-inference is not in the pipelines registry group speaker-diarization. #1516

Open san-kou7 opened 3 months ago

san-kou7 commented 3 months ago

🐛 Bug

when i run the code about-- quick_start_zh.md(FunASR/docs/modelscope_pipeline /quick_start_zh.md)

from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks

inference_diar_pipline = pipeline( mode="sond_demo", num_workers=0, task=Tasks.speaker_diarization, diar_model_config="sond.yaml", model='damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch', model_revision="v1.0.3", sv_model="damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch", sv_model_revision="v1.0.0", )

audio_list=[ "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/record.wav", "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_A.wav", "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B.wav", "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_data/spk_B1.wav" ]

results = inference_diar_pipline(audio_in=audio_list) print(results) 24-03-19 19:24:25,934 - modelscope - WARNING - ('PIPELINES', 'speaker-diarization', 'speaker-diarization-inference') not found in ast index file Traceback (most recent call last): File "/home/caopinzhi/FunASR/try/two.py", line 4, in inference_diar_pipline = pipeline( File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/pipelines/builder.py", line 170, in pipeline return build_pipeline(cfg, task_name=task) File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/pipelines/builder.py", line 65, in build_pipeline return build_from_cfg( File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/utils/registry.py", line 198, in build_from_cfg raise KeyError( KeyError: 'speaker-diarization-inference is not in the pipelines registry group speaker-diarization. Please make sure the correct version of ModelScope library is used.'

Environment

I hope you can help me solve this problem amidst your busy schedule. I would greatly appreciate it.

LauraGPT commented 3 months ago

Please install: funasr==0.8.8 modelscope==1.10.0

https://github.com/alibaba-damo-academy/FunASR/tree/v0.8.8

san-kou7 commented 3 months ago

Thank you very much for your answer, it successfully solved my above problem.But I encountered a similar problem when using the model on modelscope for inference.（iic/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary）

Bug：KeyError: 'funasr-pipeline is not in the pipelines registry group auto-speech-recognition. Please make sure the correct version of ModelScope library is used.'

Code： 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='iic/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn', model_revision='v2.0.4', vad_model='iic/speech_fsmn_vad_zh-cn-16k-common-pytorch', vad_model_revision="v2.0.4", punc_model='iic/punc_ct-transformer_cn-en-common-vocab471067-large', punc_model_revision="v2.0.4", output_dir=output_dir, ) rec_result = inference_pipeline(audio_in, batch_size_s=300, batch_size_token_threshold_s=40)

print(rec_result)

Traceback (most recent call last): File "/home/caopinzhi/FunASR/try/three.py", line 7, in inference_pipeline = pipeline( File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/pipelines/builder.py", line 170, in pipeline return build_pipeline(cfg, task_name=task) File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/pipelines/builder.py", line 65, in build_pipeline return build_from_cfg( File "/home/caopinzhi/yes/envs/fun/lib/python3.9/site-packages/modelscope/utils/registry.py", line 198, in build_from_cfg raise KeyError( KeyError: 'funasr-pipeline is not in the pipelines registry group auto-speech-recognition. Please make sure the correct version of ModelScope library is used.'

Environment Linux FunASR Version (0.8.8): ModelScope Version (1.10.0): PyTorch Version (e.g., 2.0.0): How you installed funasr ( source): Python version:3.9

I greatly appreciate that help me solve this problem again.