Model reference · open weights

wav2vec2-large-xlsr-53-842h-luxembourgish-14h

Available as managed deployment Audio Lemswasabi · community Speech→text 1 variants 4k dl/mo

wav2vec2-large-xlsr-53-842h-luxembourgish-14h is an open-weight audio or speech model from Lemswasabi. 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 byLemswasabi
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-05-21
Popularity4k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xlsr-53-842h-luxembourgish-14h is

Model description

We fine-tuned a wav2vec 2.0 large XLSR-53 checkpoint with 842h of unlabelled Luxembourgish speech collected from RTL.lu. Then the model was fine-tuned on 14h of labelled Luxembourgish speech from the same domain.

Intended uses & limitations

More information needed

Read the full model card

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 7.5e-05
  • train_batch_size: 3
  • eval_batch_size: 3
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 12
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • num_epochs: 50.0
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.20.0.dev0
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.1
  • Tokenizers 0.12.1

Citation

This model is a result of our paper IMPROVING LUXEMBOURGISH SPEECH RECOGNITION WITH CROSS-LINGUAL SPEECH REPRESENTATIONS submitted to the IEEE SLT 2022 workshop

@misc{lb-wav2vec2,
  author = {Nguyen, Le Minh and Nayak, Shekhar and Coler, Matt.},
  keywords = {Luxembourgish, multilingual speech recognition, language modelling, wav2vec 2.0 XLSR-53, under-resourced language},
  title = {IMPROVING LUXEMBOURGISH SPEECH RECOGNITION WITH CROSS-LINGUAL SPEECH REPRESENTATIONS},
  year = {2022},
  copyright = {2023 IEEE}
}

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
Speech RecognitionDev WER11.680
Speech RecognitionTest WER10.710
Speech RecognitionDev CER2.640
Speech RecognitionTest CER2.310

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wav2vec2-large-xlsr-53-842h-luxembourgish-14h for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-842h-luxembourgish-14h 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-53-842h-luxembourgish-14h" -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