Trelis/whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283

Whisper Small Pilotgpt Unified All Raw Nopack 0.5S Clean 7283

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

Training Results

Metric	Base Model	Fine-tuned
WER	53.69%	32.92%

Improvement: 20.77% WER reduction (lower is better)

Training Details

• Base Model: openai/whisper-small
• Training Dataset: Trelis/pilotgpt-unified-all-raw-nopack-0.5s-clean
• Train Loss: 0.5921
• Training Time: 16.2 minutes

Inference

from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="Trelis/whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283")
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