mirror of
https://github.com/FunAudioLLM/SenseVoice.git
synced 2025-09-15 15:08:35 +08:00
23 lines
656 B
Python
23 lines
656 B
Python
#!/usr/bin/env python3
|
|
# -*- encoding: utf-8 -*-
|
|
# Copyright FunASR (https://github.com/FunAudioLLM/SenseVoice). All Rights Reserved.
|
|
# MIT License (https://opensource.org/licenses/MIT)
|
|
|
|
from model import SenseVoiceSmall
|
|
from funasr.utils.postprocess_utils import rich_transcription_postprocess
|
|
|
|
|
|
model_dir = "iic/SenseVoiceSmall"
|
|
m, kwargs = SenseVoiceSmall.from_pretrained(model=model_dir, device="cuda:0")
|
|
|
|
|
|
res = m.inference(
|
|
data_in=f"{kwargs['model_path']}/example/en.mp3",
|
|
language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"
|
|
use_itn=False,
|
|
**kwargs,
|
|
)
|
|
|
|
text = rich_transcription_postprocess(res[0][0]["text"])
|
|
print(text)
|