wavlm-base-plus-sv is an open-weight model from losCrossos. Its published files total 404.6 MB.
The model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz.
Model Card
The model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. Note: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong…
Excerpt from the card by losCrossos.
Configuration
- Architecture
- WavLMForXVector
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 32
- Stored precision
- float32
- Model type
- wavlm
Identity and Version
- Repository
- loscrossos/wavlm-base-plus-sv
- Publisher
- losCrossos
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 2c8b3526ecbdaa560356f25865a84f5070d13895
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
5 files, 404.6 MB in total. The weights are 1 file totalling 404.5 MB in bin.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 404.5 MB | e906bce2fa42 |
| config.json | Configuration | 58.6 KB | — |
| preprocessor_config.json | Configuration | 215 B | — |
| README.md | Documentation | 4.1 KB | — |
| .gitattributes | Repository | 1.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 404.5 MB
Released by losCrossos through its official repository on Hugging Face.
Built From
- Described by arXiv:1912.07875
- Described by arXiv:2101.00390
- Described by arXiv:2106.06909
- Described by arXiv:2110.13900
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 404.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.