speech_recognition/SenseVoice
1
0
Fork 0
mirror of https://github.com/FunAudioLLM/SenseVoice.git synced 2025-09-15 15:08:35 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix api torchaudio.load bug

Browse Source
This commit is contained in:
Travis 2024-07-28 10:45:02 +08:00
parent 01dffe6563
commit abc5d30757
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
api.py
View File

@ -10,6 +10,8 @@ from enum import Enum
import torchaudio
from model import SenseVoiceSmall
from funasr.utils.postprocess_utils import rich_transcription_postprocess
from io import BytesIO
class Language(str, Enum):
auto = "auto"
@ -49,9 +51,11 @@ async def turn_audio_to_text(files: Annotated[List[bytes], File(description="wav
audios = []
audio_fs = 0
for file in files:
data_or_path_or_list, audio_fs = torchaudio.load(file)
file_io = BytesIO(file)
data_or_path_or_list, audio_fs = torchaudio.load(file_io)
data_or_path_or_list = data_or_path_or_list.mean(0)
audios.append(data_or_path_or_list)
file_io.close()
if lang == "":
lang = "auto"
if keys == "":