facebook / audio-classification updated 3 years ago

mms-lid-126

Name: mms-lid-126
Author: facebook

This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 126 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 126 lang...

Params

970 M

Context

—

Downloads 30d

308 K

Likes

Commercial use: not allowed · cc-by-nc-4.0 Not gated SAFETENSORS 158 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

308 K239 K

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	3.9 GB	4.9 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: Wav2Vec2ForSequenceClassification
Parameters: 970 M
Tensor type: F32
Vocabulary: 154
Layers / heads: 48 / 16
Licence: cc-by-nc-4.0
First seen on the Hub: 2023-06-13
Training datasets: google/fleurs
Added to our catalog: 2026-07-28

Compare with

clap-htsat-fused 6.9 M ast-finetuned-audioset-10-10-0.4593 1.2 M wav2vec2-large-robust-12-ft-emotion-msp-dim 751 K wav2vec2-large-xlsr-53-gender-recognition-librispeech 626 K MERT-v1-330M 560 K mms-lid-256 221 K

Appears in

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