Model reference · open weights

wav2vec2-960h

wav2vec2-960h is an open-weight audio or speech model from facebook, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio facebook 1 variants 1.4M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What wav2vec2-960h is

Wav2Vec2-Base-960h Facebook's Wav2Vec2 The base model pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Paper Authors: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli Abstract We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20. Usage To transcribe audio files the model can be used as a standalone acoustic model as follows: Evaluation This code snippet shows how to evaluate facebook/wav2vec2-base-960h on LibriSpeech's "clean" and "other" test data. Result (WER):

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerfacebook
TypeAudio & music
Parameters (lead)94M
Variants1
Runs withtransformers
Released2022-03-02
Popularity1.4M downloads / month
Likes402
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
wav2vec2-base-960h94MBF16~0.2 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionLibriSpeech (clean)Test WER3.4
Automatic Speech RecognitionLibriSpeech (other)Test WER8.6

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-960h for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-960h below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="wav2vec2-960h" -F file=@audio.mp3

Details

Languages, data & research

Languages

en

Trained / evaluated on

librispeech_asr

Tags

transformers pytorch tf safetensors wav2vec2 automatic-speech-recognition audio hf-asr-leaderboard en dataset:librispeech_asr model-index eval-results endpoints_compatible deploy:azure

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want wav2vec2-960h on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms