ChristophSchuhmann/vocal-music-whisper

Default checkpoint at repo root: v2/unbalanced-lr3e5 (val 0.9597), chosen on caption quality (Gemini 3.6 Flash, audio + caption, 158 held-out clips x 2 passes); inference + training + judging code and raw judgements

upload

upload

upload

upload

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload vocab.json with huggingface_hub

Upload train_meta.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload special_tokens_map.json with huggingface_hub

Upload preprocessor_config.json with huggingface_hub

Upload normalizer.json with huggingface_hub

Upload model.safetensors with huggingface_hub

Upload merges.txt with huggingface_hub

Upload history.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload added_tokens.json with huggingface_hub

upload

initial commit