Model reference · open weights

wav2vec2-large-xls-r-bulgarian

Available as managed deployment Audio infinitejoy · community Speech→text 1 variants 11k dl/mo

wav2vec2-large-xls-r-bulgarian is an open-weight audio or speech model from infinitejoy. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byinfinitejoy
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-03-02
Popularity11k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xls-r-bulgarian is

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - BG dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4487
  • Wer: 0.4674
Read the full model card

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 7e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
2.97746.335002.97691.0
1.345312.6610000.65230.6980
1.165818.9915000.56360.6359
1.079725.3220000.50040.5759
1.04431.6525000.49580.5569
0.991537.9730000.49710.5350
0.942944.335000.48290.5229
0.926650.6340000.45150.5074
0.896556.9645000.45990.5039
0.87863.2950000.47350.4954
0.849469.6255000.44600.4878
0.834375.9560000.45100.4795
0.823682.2865000.45380.4789
0.806988.6170000.45260.4748
0.795894.9475000.44960.4700

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.17.1.dev0
  • Tokenizers 0.11.0

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

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

TaskDatasetMetricScore
Automatic Speech RecognitionCommon Voice 7Test WER46.680
Automatic Speech RecognitionCommon Voice 7Test CER10.750
Automatic Speech RecognitionRobust Speech Event - Dev DataTest WER63.680
Automatic Speech RecognitionRobust Speech Event - Dev DataTest CER19.880
Automatic Speech RecognitionRobust Speech Event - Test DataTest WER64.080

Using it via the API

Call it like any OpenAI endpoint

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

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

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