Commit History
3 days ago
-
Add evaluation results
Verified signature# Add evaluation results for LiquidAI/LFM3-Audio-2B ## Summary This PR adds the benchmark results published on the model card for `LiquidAI/LFM3-Audio-2B` to `.eval_results/`, following the [Hugging Face Hub evaluation-results specification](https://huggingface.co/docs/hub/eval-results). ## Benchmarks Added - [Open ASR Leaderboard (mean WER)](https://huggingface.co/datasets/hf-audio/open-asr-leaderboard?eval_result=LiquidAI/LFM3-Audio-2B&leaderboard_task_id=mean_wer) — 6.23 ## Benchmarks Skipped (Not Registered on Hub) These benchmarks are on the model card but have no registered `eval.yaml` on the Hub: - Multilingual ASR on FLEURS (6.03) - English TTS UTMOSv2 (3.83) - VoiceBench (73.13) - Tool calling, internal eval (58.50) - MMAR (50.60) They can be added once their authors register an `eval.yaml` on the Hub. ## Source - Model card: https://huggingface.co/LiquidAI/LFM3-Audio-2B - Blog: https://www.liquid.ai/blog/lfm3 ## Files Added - `.eval_results/LFM3-Audio-2B.yaml` ##…d2a649b
4 days ago
-
LFM3-Audio-2B
Co-authored-by: orech <orech@users.noreply.huggingface.co> Co-authored-by: saniyakarwa <saniyakarwa@users.noreply.huggingface.co> Co-authored-by: haerski <haerski@users.noreply.huggingface.co> Co-authored-by: mlabonne <mlabonne@users.noreply.huggingface.co> Co-authored-by: CalderKat <CalderKat@users.noreply.huggingface.co> Co-authored-by: Paul Pak <Paul Pak@users.noreply.huggingface.co>9d49701
