Fix the variable name (#2328)

majic31

2024-12-24 23e7ddebccd3b05cf7ef89809bcfe565ad6dfa1f

 examples/industrial_data_pretraining/sense_voice/demo.py

@@ -1,24 +1,113 @@
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# Copyright FunASR (https://github.com/FunAudioLLM/SenseVoice). All Rights Reserved.
#  MIT License  (https://opensource.org/licenses/MIT)

from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess

model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/SenseVoice",
                  vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
              vad_kwargs={"max_single_segment_time": 30000},
                  )
model_dir = "iic/SenseVoiceSmall"


input_wav = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/SenseVoice/aed_ser/asr_bgm.wav"
model = AutoModel(
    model=model_dir,
    vad_model="fsmn-vad",
    vad_kwargs={"max_single_segment_time": 30000},
    device="cuda:0",
)

DecodingOptions = {
   "task": ("ASR", "AED", "SER"),
   "language": "auto",
   "fp16": True,
   "gain_event": True,
   }
# en
res = model.generate(
    input=f"{model.model_path}/example/en.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

res = model.generate(input=input_wav, batch_size_s=0, DecodingOptions=DecodingOptions)
# en with timestamp
res = model.generate(
    input=f"{model.model_path}/example/en.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
    output_timestamp=True,
)
print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

# zh
res = model.generate(
    input=f"{model.model_path}/example/zh.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

# zh with timestamp
res = model.generate(
    input=f"{model.model_path}/example/zh.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
    output_timestamp=True,
)
print(res)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

# yue
res = model.generate(
    input=f"{model.model_path}/example/yue.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

# ja
res = model.generate(
    input=f"{model.model_path}/example/ja.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)


# ko
res = model.generate(
    input=f"{model.model_path}/example/ko.mp3",
    cache={},
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)