funasr1.0 modelscope

游雁

2024-01-09 d8b586e02cd14f7eed6b330bd4f110cb1e7f24ad

 examples/industrial_data_pretraining/paraformer/demo.py

@@ -5,17 +5,17 @@

from funasr import AutoModel

model = AutoModel(model="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revison="v2.0.0")

res = model(input="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav")
res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
print(res)


from funasr import AutoFrontend

frontend = AutoFrontend(model="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
frontend = AutoFrontend(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", model_revison="v2.0.0")

fbanks = frontend(input="../modelscope_models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav", batch_size=2)
fbanks = frontend(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", batch_size=2)

for batch_idx, fbank_dict in enumerate(fbanks):
   res = model(**fbank_dict)