Model reference · open weights

xls-r-sv-robust

Available as managed deployment Audio marinone94 · community Speech→text 1 variants 752 dl/mo

xls-r-sv-robust is an open-weight audio or speech model from marinone94. 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 bymarinone94
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-03-02
Popularity752 downloads / month
LicenceOpen weights

About

What xls-r-sv-robust is

It achieves the following results on the evaluation set ("test" split, without LM):

  • Loss: 0.1318
  • Wer: 0.1121
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: 7.5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.2
  • num_epochs: 100.0
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
2.909910.4210002.83691.0
1.074520.8320000.19570.1673
0.93431.2530000.15790.1389
0.869141.6640000.14570.1290
0.832852.0850000.14350.1205
0.806862.560000.13500.1191
0.782272.9170000.13470.1155
0.776983.3380000.13210.1131
0.767893.7590000.13210.1115

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 2.2.2
  • 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 Recognitionmozilla-foundation/common_voice_9_0Test WER7.720
Automatic Speech Recognitionmozilla-foundation/common_voice_9_0Test CER2.610
Automatic Speech Recognitionspeech-recognition-community-v2/dev_dataTest WER16.230
Automatic Speech Recognitionspeech-recognition-community-v2/dev_dataTest CER8.210
Automatic Speech Recognitionspeech-recognition-community-v2/dev_dataTest WER15.080
Automatic Speech Recognitionspeech-recognition-community-v2/dev_dataTest CER7.510

Using it via the API

Call it like any OpenAI endpoint

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