SAVRN
Search Contact SAVRN

Open-weight model

wav2vec2-base

by AI at Meta facebook/wav2vec2-base

The base model 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.

Parameters
Context
Weights380.3 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.8M

SAVRN's Notes on wav2vec2-base

Sixteen kilohertz in, speech representations out. That is the contract with this base model from AI at Meta: pretrained on audio alone, shipped without a tokenizer, and a speech recognizer only once you build one and fine-tune on labeled text. Eight PyTorch files total 380 MB, so the hardware question is your fine-tuning run, not holding the weights. Our Index has no memory row or token price for it, which fits a model you fine-tune rather than call.

Apache 2.0 allows commercial use, modification and redistribution, so a fine-tuned derivative can ship in a product provided the license, copyright notices and any NOTICE file travel with it and you state what you changed. Check two things: the pretraining corpus is librispeech_asr, so weigh how far your own audio sits from it, and the weights date to December 2021 and have not moved, which makes the fine-tune entirely your work.

Model Card

By AI at Meta, published under apache-2.0, revision 0b5b8e868dd8.

Facebook's Wav2Vec2

The base model 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 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.

Paper

Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli

Read the full model card (247 words)

Configuration

Architecture
Wav2Vec2ForPreTraining
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
32
Model type
wav2vec2

Identity and Version

Repository
facebook/wav2vec2-base
Publisher
AI at Meta
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
en
Revision
0b5b8e868dd84f03fd87d01f9c4ff0f080fecfe8
First published
2022-03-02
Last updated
2021-12-28

Files and Weights

8 files, 380.3 MB in total. The weights are 1 file totalling 380.3 MB in bin.

Weights1 file · 380.3 MB
Configuration3 files · 2.1 KB
Tokenizer2 files · 454 B
Documentation1 file · 2.0 KB
Repository1 file · 736 B
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights380.3 MB 3249fe98bfc6
config.jsonConfiguration1.8 KB
preprocessor_config.jsonConfiguration159 B
special_tokens_map.jsonConfiguration85 B
README.mdDocumentation2.0 KB
.gitattributesRepository736 B
tokenizer_config.jsonTokenizer163 B
vocab.jsonTokenizer291 B

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
380.3 MB
Download from AI at Meta

Released by AI at Meta through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published380.3 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About wav2vec2-base

Can I use wav2vec2-base commercially?

Yes. wav2vec2-base is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.