Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
nsfwalex
/
whisper-transcribe-new
like
3
Runtime error
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
3c30a0a
whisper-transcribe-new
36.8 kB
2 contributors
History:
73 commits
liuyang
try add token
3c30a0a
4 months ago
.gitattributes
1.52 kB
initial commit
6 months ago
README.md
291 Bytes
update Gradio SDK version to 5.0.1 in README and requirements
6 months ago
app.py
32.8 kB
try add token
4 months ago
config.py
1.52 kB
update model
6 months ago
requirements.txt
698 Bytes
Implement audio preprocessing and speaker diarization enhancements in WhisperTranscriber. Introduce methods for audio chunk preparation, VAD-based trimming, and speaker embedding extraction. Update process_audio methods to utilize task JSON for improved workflow and metadata handling. Add webrtcvad dependency for voice activity detection.
4 months ago