YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

911 Voice-to-Text Transcription Model (20 Epochs)

This is a specialized Whisper-based model trained on 911 emergency call recordings for accurate real-time voice-to-text transcription.

Performance

  • Training Epochs: 20
  • Coherence Score: 82%
  • Model Size: Base Whisper
  • Real-time Capable: Yes

Usage

from transformers import WhisperProcessor, WhisperForConditionalGeneration

processor = WhisperProcessor.from_pretrained("vaishnavanand/911-voice-to-text-20epochs")
model = WhisperForConditionalGeneration.from_pretrained("vaishnavanand/911-voice-to-text-20epochs")

Emergency Keywords

Help, Emergency, 911, Urgent, Critical, Accident, Fire, Police, Ambulance, Medical, Shooting, Robbery, Assault, Heart Attack, Stroke, Bleeding, Unconscious, Breathing, Chest Pain, Gun, Knife, Weapon, Crash, Trapped

License

MIT License - Free for commercial and research use.

Downloads last month
1
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support