Model reference · open weights

wav2vec2-large-xlsr-53-russian

wav2vec2-large-xlsr-53-russian is an open-weight audio or speech model from jonatasgrosman, 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 jonatasgrosman 1 variants 3.7M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What wav2vec2-large-xlsr-53-russian is

Fine-tuned XLSR-53 large model for speech recognition in Russian Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint Usage The model can be used directly (without a language model) as follows... Using the HuggingSound library: Writing your own inference script: Evaluation 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata Citation If you want to cite this model you can use this:

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

Specifications

What it is

Makerjonatasgrosman
TypeAudio & music
Variants1
Runs withtransformers
Released2022-03-02
Popularity3.7M downloads / month
Likes76
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-large-xlsr-53-russianBF16Weights ↗

Benchmarks

Reported results

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

TaskDatasetMetricScore
Automatic Speech RecognitionCommon Voice ruTest WER13.3
Automatic Speech RecognitionCommon Voice ruTest CER2.88
Automatic Speech RecognitionCommon Voice ruTest WER (+LM)9.57
Automatic Speech RecognitionCommon Voice ruTest CER (+LM)2.24
Automatic Speech RecognitionRobust Speech Event - Dev DataDev WER40.22
Automatic Speech RecognitionRobust Speech Event - Dev DataDev CER14.8
Automatic Speech RecognitionRobust Speech Event - Dev DataDev WER (+LM)33.61
Automatic Speech RecognitionRobust Speech Event - Dev DataDev CER (+LM)13.5

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-large-xlsr-53-russian for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-russian 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-large-xlsr-53-russian" -F file=@audio.mp3

Details

Languages, data & research

Languages

ru

Trained / evaluated on

common_voice mozilla-foundation/common_voice_6_0

Tags

transformers pytorch jax wav2vec2 automatic-speech-recognition audio hf-asr-leaderboard mozilla-foundation/common_voice_6_0 robust-speech-event ru speech xlsr-fine-tuning-week dataset:common_voice dataset:mozilla-foundation/common_voice_6_0

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-large-xlsr-53-russian 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