sageTheDm/interstellar_ai
1
0
Fork 0
forked from React-Group/interstellar_ai
Code Pull requests Activity

main #28

Merged
sageTheDm merged 14 commits from React-Group/interstellar_ai:main into main 2024-09-30 12:53:09 +02:00
Conversation 0 Commits 14 Files changed 22 +9 -15
1 changed files with 9 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 1e05319266 - Show all commits

24
py/voice.py
View file

@ -7,25 +7,19 @@ class VoiceRecognition:
@staticmethod
def recognition(audio):
audio_buffer = io.BytesIO(audio.read())
try:
audio_segment = AudioSegment.from_file(audio_buffer, format="ogg")
wav_io = io.BytesIO()
audio_segment.export(wav_io, format="wav")
wav_io.seek(0)
except:
print("audio to wav failed")
audio_segment = AudioSegment.from_file(audio_buffer, format="ogg")
wav_io = io.BytesIO()
audio_segment.export(wav_io, format="wav")
wav_io.seek(0)
model_size = "base"
model = WhisperModel(model_size, device="cpu", compute_type=" ")
model = WhisperModel(model_size, device="cpu", compute_type="int8")
segments, _ = model.transcribe(wav_io)
transcription = ""
for segment in segments:
transcription += segment.text + " "
result = transcription.strip()
print(result)
return result
# npm install @ffmpeg/ffmpeg @ffmpeg/util @ffmpeg/types @ffmpeg/core-mt