Model reference · open weights

wav2vec2-xls-r-bengali

wav2vec2-xls-r-bengali is an open-weight audio or speech model from arijitx, 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 arijitx 1 variants 934k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What wav2vec2-xls-r-bengali is

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the OPENSLRSLR53 - bengali dataset. It achieves the following results on the evaluation set. Without language model : - WER: 0.21726385291857586 - CER: 0.04725010353701041 With 5 gram language model trained on 30M sentences randomly chosen from AI4Bharat IndicCorp dataset : - WER: 0.15322879016421437 - CER: 0.03413696666806267 Note : 5% of a total 10935 samples have been used for evaluation. Evaluation set has 10935 examples which was not part of training training was done on first 95% and eval was done on last 5%. Training was stopped after 180k steps. Output predictions are available under files section. Training hyperparameters The following hyperparameters were used during training: - datasetname="openslr" - modelnameorpath="facebook/wav2vec2-xls-r-300m" - datasetconfigname="SLR53" - outputdir="./wav2vec2-xls-r-300m-bengali" - overwriteoutputdir - numtrainepochs="50" - perdevicetrainbatchsize="32" - perdeviceevalbatchsize="32" - gradientaccumulationsteps="1" - learningrate="7.5e-5" - warmupsteps="2000" - lengthcolumnname="inputlength" - evaluationstrategy="steps" - textcolumnname="sentence" - charstoignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – - savesteps="2000" - evalsteps="3000" - loggingsteps="100" - layerdrop="0.0" - activationdropout="0.1" - savetotallimit="3" - freezefeatureencoder - featprojdropout="0.0" - masktimeprob="0.75" - masktimelength="10" - maskfeatureprob="0.25" - maskfeaturelength="64" - preprocessingnumworkers 32 Framework versions - Transformers 4.16.0.dev0 - Pytorch 1.10.1+cu102 - Datasets 1.17.1.dev0 - Tokenizers 0.11.0 Notes - Training and eval code modified from : https://github.com/huggingface/transformers/tree/master/examples/researchprojects/robust-speech-event. - Bengali speech data was not available from common voice or librispeech multilingual datasets, so OpenSLR53 has been used. - Minimum audio duration of 0.5s has been used to filter the training data which excluded may be 10-20 samples. - OpenSLR53 transcripts are not part of LM training and LM used to evaluate.

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

Specifications

What it is

Makerarijitx
TypeAudio & music
Variants1
Runs withtransformers
Released2022-03-02
Popularity934k downloads / month
Likes10
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-xls-r-300m-bengaliBF16Weights ↗

Benchmarks

Reported results

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

TaskDatasetMetricScore
Speech RecognitionOpen SLRTest WER0.217
Speech RecognitionOpen SLRTest CER0.047
Speech RecognitionOpen SLRTest WER with lm0.153
Speech RecognitionOpen SLRTest CER with lm0.034

Using it via the API

Call it like any OpenAI endpoint

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

Details

Languages, data & research

Languages

bn

Trained / evaluated on

openslr SLR53 AI4Bharat/IndicCorp

Tags

transformers pytorch wav2vec2 automatic-speech-recognition bn hf-asr-leaderboard openslr_SLR53 robust-speech-event dataset:openslr dataset:SLR53 dataset:AI4Bharat/IndicCorp model-index endpoints_compatible

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-xls-r-bengali 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