Model reference · open weights

wav2vec2-large-xls-r-frisian

Available as managed deployment Audio greenw0lf · community Speech→text 1 variants 1k dl/mo

wav2vec2-large-xls-r-frisian is an open-weight audio or speech model from greenw0lf. 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 bygreenw0lf
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2023-03-26
Popularity1k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xls-r-frisian is

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2204
  • Wer: 0.1493
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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 30
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
4.96062.453002.61841.0
1.49924.96000.42330.4143
0.97577.359000.27650.3021
0.87739.812000.25290.2528
0.744812.2415000.23630.2258
0.703914.6918000.22580.2103
0.681117.1421000.22170.2074
0.627919.5924000.20500.1915
0.593822.0427000.22290.1922
0.622724.4930000.20880.2019
0.568226.9433000.21270.1874
0.593929.3936000.20440.1789
0.542731.8439000.21850.1791
0.555134.4142000.20970.1644
0.502136.8645000.21800.1678
0.458939.3148000.20760.1581
0.520441.7651000.21810.1587
0.51244.2154000.22630.1607
0.46546.6657000.22040.1493

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu117
  • Datasets 2.11.0
  • Tokenizers 0.13.3

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_13_0Wer0.149
Automatic Speech Recognitioncommon_voice_8_0Wer0.154
Automatic Speech Recognitioncommon_voice_13_0Wer0.147

Using it via the API

Call it like any OpenAI endpoint

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