laion/voiceclap-large-v2
feature-extraction model by laion
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. cross-entropy of audio embeddings vs prototypes on pseudo-labeled clips. 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. Same-commit comparison on the VoiceNet harness: Controlled A/B vs its exact no-PCL twin (identical data/recipe, ep1): Ensemble notes: averaging this model's similarities with gijs/voiceclap-lco-7b-lora and the k=10 MOSS variant sets the current…
Read the full model card ↗ · Preview checked 2026-10-31T05:43:13.124Z
Inside the original model card — Document outline
- VoiceCLAP-Large-v2 (PCL)
- What's new vs voiceclap-large
- Evaluation (VoiceNet benchmark, human-annotated)
- Training recipe
- Quick start
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
laion/voiceclap-large-v2 is a feature-extraction model repository published by laion on Hugging Face. The source reports the sentence-transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- sentence-transformers
- Recent downloads (30 days)
- 103,567
- Cumulative likes
- 12
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 8,931,813,888
- Architecture
- Qwen2_5OmniThinkerForConditionalGeneration
- License
- cc-by-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-06-11T05:19:46.000Z
- Last modified
- 2026-09-09T14:59:37.000Z
Compatibility and lineage
Reported languages: en, de, fr, es, zh
Reported base models: LCO-Embedding/LCO-Embedding-Omni-7B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:54:29.511Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.