SenseVoice/demo2.py
2024-07-22 15:27:56 +08:00

18 lines
467 B
Python

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", # "zn", "en", "yue", "ja", "ko", "nospeech"
use_itn=False,
**kwargs,
)
text = rich_transcription_postprocess(res[0][0]["text"])
print(text)