CoolFace
Modelpublic

noflm/whisper-ft-jdd-topic1-20251224-cliponly-small-epoch10

sourceHugging Facemitupdated 8mo agoView on Hugging Face
0likes
Model Card

Whisper Fine-tuning Experiment: jddtopic120251224-cliponly_sample100-whisper-small-epoch10

Model Description

This model contains a complete Whisper fine-tuning experiment including:

  • —Training checkpoints (SpeechBrain format)
  • —Final model (Transformers format)
  • —Test results and evaluation metrics
  • —Training history visualizations

Model Information

Test Results

  • —WER: N/A
  • —CER: N/A
  • —Test Loss: N/A

Contents

├── checkpoints/          # Training checkpoints
│   ├── CKPT+epoch_*/    # Per-epoch checkpoints
│   ├── CKPT+BEST_WER/   # Best WER checkpoint
│   └── CKPT+FINAL/      # Final checkpoint
├── final_model/          # Transformers-compatible model
│   ├── config.json      # Model configuration
│   ├── model.safetensors # Model weights
│   ├── preprocessor_config.json
│   ├── tokenizer_config.json
│   └── ...
├── test_results.json     # Test metrics
├── detailed_metrics.json # Detailed training history
├── training_history_speechbrain.png  # Training curves
└── training_report_speechbrain.txt   # Summary report

Usage

Load checkpoint (SpeechBrain format)

python
import torch
checkpoint = torch.load('checkpoints/CKPT+BEST_WER/model.ckpt')

Load final model (Transformers format)

python
from transformers import WhisperForConditionalGeneration, WhisperProcessor

model = WhisperForConditionalGeneration.from_pretrained("./final_model")
processor = WhisperProcessor.from_pretrained("./final_model")

Citation

If you use this experiment data, please cite the original Whisper paper:

bibtex
@article{radford2022robust,
  title={Robust speech recognition via large-scale weak supervision},
  author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  journal={arXiv preprint arXiv:2212.04356},
  year={2022}
}