Hugging Face's logo

facebook
/
wav2vec2-large-it-voxpopuli

Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
Italian
wav2vec2
pretraining
audio
voxpopuli
Inference Endpoints
Model card Files Community
1
wav2vec2-large-it-voxpopuli / README.md
patrickvonplaten's picture
patrickvonplaten
correct readme
bd5c278
preview code
|
raw
history blame contribute delete
1.05 kB
metadata
language: it
tags:
  - audio
  - automatic-speech-recognition
  - voxpopuli
license: cc-by-nc-4.0

Wav2Vec2-Large-VoxPopuli

Facebook's Wav2Vec2 large model pretrained on the it unlabeled subset of VoxPopuli corpus.

Paper: VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

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

Fine-Tuning

Please refer to this blog on how to fine-tune this model on a specific language. Note that you should replace "facebook/wav2vec2-large-xlsr-53" with this checkpoint for fine-tuning.