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 -
Add admin panel for model training with SSE progress
814cdd0 -
Retrain model on input_data.csv embeddings with PCA(256d), threshold=0.4
d18bcaf -
Fix model architecture: add PCA transform (2051->256d) to match training pipeline
6a10fdd -
Add Git LFS tracking and update gitignore for HF Spaces
97bb281 -
Deploy to Hugging Face Spaces
26fbacc -
added model
4ee83ba -
added dockerfile
2095428 -
added web interface
f9f7fd7 -
Merge branch 'Utkarsharma7:main' into main
edd68ad -
deleted some files
89b0f10 -
Merge pull request #2 from Utkarsharma7/revert-1-main
Revert "added web interface and a pre trained model"e56f5a5 -
Revert "added web interface and a pre trained model"
3811d90 -
Final change
508969a -
Merge pull request #1 from Neev-Rathod/main
added web interface and a pre trained modelad6aefd -
Merge branch 'main' into main
67c0673 -
added web interface
f4a0f54 -
Updated with cnn and comparision with cnn,mlp done
25f659b -
cnn but not tested
Sarthak-gupta-cpp637a5d2 -
less accuracy better graph
Sarthak-gupta-cpp4956353 -
changes
Sarthak-gupta-cpp4dc7304 -
Updated
5e96656
-
added pretrained models
6973ba9 -
Updated lowerd overfitting
e78ba98 -
Arabic-only: prosody layers, remove English, add test metrics, anti-overfitting, FLOW.md
Made-with: Cursorc4a7a0e
-
Added classification for english also
8a912c1 -
Changed to XLSR model
875a0a4
-
Created a git ignore file
ae9331e -
Initial commit
cdfb7d6