Merge pull request #2382 from msgk239/dev_clean

Shi Xian

2025-02-18 57e023e5cfa522007e24d87c8e3d82bf7c4a19cd

 examples/industrial_data_pretraining/sense_voice/demo.py

@@ -1,8 +1,7 @@
#!/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
@@ -21,12 +20,27 @@
res = model.generate(
    input=f"{model.model_path}/example/en.mp3",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    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)

# 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)

@@ -34,7 +48,7 @@
res = model.generate(
    input=f"{model.model_path}/example/zh.mp3",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
@@ -43,11 +57,26 @@
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",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
@@ -60,7 +89,7 @@
res = model.generate(
    input=f"{model.model_path}/example/ja.mp3",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
@@ -74,7 +103,7 @@
res = model.generate(
    input=f"{model.model_path}/example/ko.mp3",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    language="auto",  # "zh", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #