AIが動く。未来が更新される。voiceclap-large-v2
A rank-16 LoRA finetune of **LCO-Embedding-Omni-7B** (Qwen2.5-Omni thinker) trained with **InfoNCE + Prototypical Contrastive loss (PCL)** on the VoiceCLAP 9-corpus mix with MOSS-Audio k=2 sampled captions. Successor to `laion/voiceclap-large` — **better on every benchmark we measure**. 1. **PCL auxiliary loss (weight 0.1)**: 39 learned emotion prototypes; cross-entropy of audio embeddings vs prototypes on pseudo-labeled clips. 2. **z-scored pseudo-labels**: emolia's `emotion_annotation` scalars, argmax over per-emotion z-scores vs corpus base rates (raw argmax is degenerate — high-base-rate dimensions win ~99% of clips). z ≥ 1.5 labels ~80-98% of emolia across all 39 emotion classes. 3. LoRA rank 16 (α=32) — rank shown equivalent to r=32 in a controlled A/B. Ensemble notes: averaging this model's similarities with `gijs/voiceclap-lco-7b-lora` and the k=10 MOSS variant sets the current VoiceNet records (Emo bal@pp 0.7102; Ext bal@pp 0.6883).
翻訳準備中のため原文を表示しています
A rank-16 LoRA finetune of **LCO-Embedding-Omni-7B** (Qwen2.5-Omni thinker) trained with **InfoNCE + Prototypical Contrastive loss (PCL)** on the VoiceCLAP 9-corpus mix with MOSS-Audio k=2 sampled captions. Successor to `laion/voiceclap-large` — **better on every benchmark we measure**. 1. **PCL auxiliary loss (weight 0.1)**: 39 learned emotion prototypes; cross-entropy of audio embeddings vs prototypes on pseudo-labeled clips. 2. **z-scored pseudo-labels**: emolia's `emotion_annotation` scalars, argmax over per-emotion z-scores vs corpus base rates (raw argmax is degenerate — high-base-rate dimensions win ~99% of clips). z ≥ 1.5 labels ~80-98% of emolia across all 39 emotion classes. 3. LoRA rank 16 (α=32) — rank shown equivalent to r=32 in a controlled A/B. Ensemble notes: averaging this model's similarities with `gijs/voiceclap-lco-7b-lora` and the k=10 MOSS variant sets the current VoiceNet records (Emo bal@pp 0.7102; Ext bal@pp 0.6883).