YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Hebrew Whisper Model - Fixed Version
Training Details
- Base Model: openai/whisper-small
- Training Rounds: 2
- Total Samples Used: 13264
- Best Evaluation Loss: 2.9681
- Final Model Location: /content/drive/MyDrive/python_projact/Speech2taxt_he/ml/model/final_model
Key Improvements:
- Fixed text processing - preserves mixed content
- Improved learning rate and batch size
- Reduced epochs to prevent overfitting
- Better audio normalization
Usage
from transformers import WhisperProcessor, WhisperForConditionalGeneration
processor = WhisperProcessor.from_pretrained('/content/drive/MyDrive/python_projact/Speech2taxt_he/ml/model/final_model')
model = WhisperForConditionalGeneration.from_pretrained('/content/drive/MyDrive/python_projact/Speech2taxt_he/ml/model/final_model')
- Downloads last month
- 12
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support