提交

kongdeqiang

5 天以前 28ccfbfc51068a663a80764e14074df5edf2b5ba

 examples/industrial_data_pretraining/seaco_paraformer/demo.py

@@ -5,27 +5,26 @@

from funasr import AutoModel

model = AutoModel(model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
                  model_revision="v2.0.4",
                  vad_model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
                  vad_model_revision="v2.0.4",
                  punc_model="damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
                  punc_model_revision="v2.0.4",
                  spk_model="damo/speech_campplus_sv_zh-cn_16k-common",
                  spk_model_revision="v2.0.2",
                  )
model = AutoModel(
    model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
    # vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
    # punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
    # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
)


# example1
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
                     hotword='达摩院 魔搭',
                     # preset_spk_num=2,
                     # sentence_timestamp=True,  # return sentence level information when spk_model is not given
                    )
res = model.generate(
    input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
    hotword="达摩院 魔搭",
    # return_raw_text=True,     # return raw text recognition results splited by space of equal length with timestamp
    # preset_spk_num=2,         # preset speaker num for speaker cluster model
    # sentence_timestamp=True,  # return sentence level information when spk_model is not given
)
print(res)


'''
"""
# tensor or numpy as input
# example2
import torchaudio
@@ -42,4 +41,4 @@
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
res = model.generate(input=[speech], batch_size_s=300, is_final=True)
'''
"""