---
title: wav2vec2-base-cs-voxpopuli-v2
canonical_url: "https://www.modelscope.cn/models/facebook/wav2vec2-base-cs-voxpopuli-v2"
md_url: "https://www.modelscope.cn/models/facebook/wav2vec2-base-cs-voxpopuli-v2.md"
repository: facebook/wav2vec2-base-cs-voxpopuli-v2
last_updated: 2025-05-20
license: cc-by-nc-4.0
model_type:
  - wav2vec2
architectures:
  - Wav2Vec2ForPreTraining
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - cs
downloads: 331
stars: 0
tags:
  - audio
  - automatic-speech-recognition
  - voxpopuli-v2
---

# wav2vec2-base-cs-voxpopuli-v2

> wav2vec2-base-cs-voxpopuli-v2 - facebook 在 ModelScope 开源的模型。Wav2Vec2-base-VoxPopuli-V2

facebook/wav2vec2-base-cs-voxpopuli-v2 是 ModelScope 魔搭社区上的机器学习模型，采用 cc-by-nc-4.0 许可。

- **Repository**: facebook/wav2vec2-base-cs-voxpopuli-v2
- **License**: cc-by-nc-4.0
- **Tags**: audio, automatic-speech-recognition, voxpopuli-v2
- **Downloads**: 331
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/wav2vec2-base-cs-voxpopuli-v2

---

# Wav2Vec2-base-VoxPopuli-V2

[Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) base model pretrained only in **cs** on **18.7k** unlabeled datat of the [VoxPopuli corpus](https://arxiv.org/abs/2101.00390).

The model is pretrained on 16kHz sampled speech audio. 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 for **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data in **cs**. Check out [this blog](https://huggingface.co/blog/fine-tune-xlsr-wav2vec2) for a more in-detail explanation of how to fine-tune the model. 

**Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*

**Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*.

See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/).