Spaces:
Sleeping
Sleeping
Commit History
-
CRITICAL FIX: Use correct Wav2Vec2 model (lv-60-espeak-cv-ft) matching training
- app.py inference was using wav2vec2-large-xlsr-53 but model was trained on wav2vec2-lv-60-espeak-cv-ft embeddings -> always wrong predictions - Dockerfile: pre-download correct model (lv-60-espeak-cv-ft) - Language dropdown now optional for audio/URL classification - Add model download endpoint for admin panel (ephemeral HF storage) - Add Download Model button in admin results00ebb72 -
Fix model architecture: add PCA transform (2051->256d) to match training pipeline
6a10fdd -
added model
4ee83ba -
added dockerfile
2095428