Trelis/whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772

Whisper Small Pilotgpt Unified All Data Lowercase Data Prep 6772

Fine-tuned Whisper model based on openai/whisper-small.

Training Results

Metric	Base Model	Fine-tuned
WER	53.69%	27.54%

Improvement: 26.15% WER reduction (lower is better)

Training Details

• Base Model: openai/whisper-small
• Training Dataset: Trelis/pilotgpt-unified-all-data-lowercase-data-prep
• Train Loss: 0.6250
• Training Time: 5.2 minutes

Inference

from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="Trelis/whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772")
result = asr("path/to/audio.wav")
print(result["text"])

Training Logs

Full training logs are available in training_log.txt.

---

Fine-tuned using Trelis Studio