vasistalodagala/whisper-finetune
Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.
Provides embedding extraction utilities across different Whisper layer depths and supports distributed multi-GPU training with step-based or epoch-based scheduling. Integrates with Hugging Face's seq2seq training pipeline and datasets library, while enabling custom dataset ingestion through standardized audio/text file formats and optional JAX-accelerated evaluation for faster inference.
361 stars. No commits in the last 6 months.
Stars
361
Forks
87
Language
Python
License
MIT
Category
Last pushed
May 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/vasistalodagala/whisper-finetune"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
linto-ai/whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
argmaxinc/WhisperKit
On-device Speech Recognition for Apple Silicon
yeyupiaoling/Whisper-Finetune
Fine-tune the Whisper speech recognition model to support training without timestamp data,...
xenova/whisper-web
ML-powered speech recognition directly in your browser
Pikurrot/whisper-gui
A simple GUI to use Whisper.