---
language: en
datasets:
- superb
tags:
- speech
- audio
- wav2vec2
- audio-classification
license: apache-2.0
---
# Model Card for wav2vec2-base-superb-sv
 
 
# Model Details
 
## Model Description
 
 
- **Developed by:** Shu-wen Yang et al.
- **Shared by:** Anton Lozhkov
- **Model type:** Wav2Vec2 with an XVector head
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Related Models:**
  - **Parent Model:** wav2vec2-large-lv60
- **Resources for more information:** 
    - [GitHub Repo](https://github.com/s3prl/s3prl/tree/master/s3prl/downstream/sv_voxceleb1)
 	 - [Associated Paper](https://arxiv.org/abs/2105.010517)
 
 
# Uses
 
 
## Direct Use
 
This is a ported version of 
[S3PRL's Wav2Vec2 for the SUPERB Speaker Verification task](https://github.com/s3prl/s3prl/tree/master/s3prl/downstream/sv_voxceleb1).

The base model is [wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60), which is pretrained on 16kHz 
sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. 

For more information refer to [SUPERB: Speech processing Universal PERformance Benchmark](https://arxiv.org/abs/2105.01051)
 
## Out-of-Scope Use
 
The model should not be used to intentionally create hostile or alienating environments for people.
 
# Bias, Risks, and Limitations
 
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
 
 
## Recommendations
 
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 
# Training Details
 
## Training Data
 
See the [superb dataset card](https://huggingface.co/datasets/superb)
 
## Training Procedure
 
 
### Preprocessing
 
More information needed
 
### Speeds, Sizes, Times
 
More information needed
 
# Evaluation
 
 
## Testing Data, Factors & Metrics
 
### Testing Data
 
See the [superb dataset card](https://huggingface.co/datasets/superb)
 
### Factors
 
 
### Metrics
 
More information needed
## Results 
 
More information needed
 
# Model Examination
 
More information needed
 
# Environmental Impact
 
 
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
- **Hardware Type:** More information needed
- **Hours used:** More information needed
- **Cloud Provider:** More information needed
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
 
# Technical Specifications [optional]
 
## Model Architecture and Objective
 
More information needed
 
## Compute Infrastructure
 
More information needed
 
### Hardware
 
More information needed
 
### Software
More information needed
 
# Citation
 
 
**BibTeX:**
 ```
@misc{https://doi.org/10.48550/arxiv.2006.11477,
  doi = {10.48550/ARXIV.2006.11477},
  
  url = {https://arxiv.org/abs/2006.11477},
  
  author = {Baevski, Alexei and Zhou, Henry and Mohamed, Abdelrahman and Auli, Michael},
  
  keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
  
  title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  
  publisher = {arXiv},


@misc{https://doi.org/10.48550/arxiv.2105.01051,
  doi = {10.48550/ARXIV.2105.01051},
  
  url = {https://arxiv.org/abs/2105.01051},
  
  author = {Yang, Shu-wen and Chi, Po-Han and Chuang, Yung-Sung and Lai, Cheng-I Jeff and Lakhotia, Kushal and Lin, Yist Y. and Liu, Andy T. and Shi, Jiatong and Chang, Xuankai and Lin, Guan-Ting and Huang, Tzu-Hsien and Tseng, Wei-Cheng and Lee, Ko-tik and Liu, Da-Rong and Huang, Zili and Dong, Shuyan and Li, Shang-Wen and Watanabe, Shinji and Mohamed, Abdelrahman and Lee, Hung-yi},
  
  keywords = {Computation and Language (cs.CL), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
  
  title = {SUPERB: Speech processing Universal PERformance Benchmark},
  
  publisher = {arXiv},
  
  year = {2021},
}


```

 
# Glossary [optional]
More information needed
 
# More Information [optional]
 
More information needed
 
# Model Card Authors [optional]
 
 
Anton Lozhkov in collaboration with Ezi Ozoani and the Hugging Face team
 
# Model Card Contact
 
More information needed
 
# How to Get Started with the Model
 
Use the code below to get started with the model.
 
<details>
<summary> Click to expand </summary>

```python
from transformers import AutoProcessor, AutoModelForAudioXVector
 
processor = AutoProcessor.from_pretrained("anton-l/wav2vec2-base-superb-sv")
 
model = AutoModelForAudioXVector.from_pretrained("anton-l/wav2vec2-base-superb-sv")
 
```
</details>