Model reference · open weights

wav2vec2-large-xls-r-welsh

Available as managed deployment Audio infinitejoy · community Speech→text 1 variants 574k dl/mo

wav2vec2-large-xls-r-welsh 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
Popularity574k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xls-r-welsh is

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

  • Loss: 0.2650
  • Wer: 0.2702
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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 3000
  • num_epochs: 50.0
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
1.34548.230000.49260.5703
1.120216.3960000.35290.3944
1.005824.5990000.31430.3341
0.928732.79120000.28960.2980
0.884940.98150000.27270.2798
0.866549.18180000.26620.2696

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.18.3
  • 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 WER31.003
Automatic Speech RecognitionCommon Voice 7Test CER7.775

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-large-xls-r-welsh for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xls-r-welsh 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-welsh" -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