facebook / automatic-speech-recognition updated 3 years ago

wav2vec2-base-960h

Name: wav2vec2-base-960h
Author: facebook

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.

Params

90 M

Context

—

Downloads 30d

1.7 M

Likes

401

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.8 M1.5 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.4 GB	0.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Wav2Vec2ForCTC
Parameters: 90 M
Tensor type: F32
Vocabulary: 32
Layers / heads: 12 / 12
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: librispeech_asr
LibriSpeech (clean) (reported): 3.4
LibriSpeech (other) (reported): 8.6
Added to our catalog: 2026-07-28

Compare with

speaker-diarization-3.1 8.9 M whisperkit-coreml 8.3 M speaker-diarization-community-1 5.3 M whisper-base 4.8 M wav2vec2-large-xlsr-53-portuguese 4.6 M wav2vec2-large-xlsr-53-russian 4.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB