AxForge
Sign in Get started

Model reference · open weights

wav2vec2-large-xlsr-tamil-commonvoice

Available as managed deployment Audio nikhil6041 · community Speech→text 1 variants 1k dl/mo

wav2vec2-large-xlsr-tamil-commonvoice is an open-weight audio or speech model from nikhil6041. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Request deployment All audio & music

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

What it is

Released bynikhil6041
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-03-02
Popularity1k downloads / month
LicenceOpen weights

About

What wav2vec2-large-xlsr-tamil-commonvoice is

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6145
  • Wer: 0.8512
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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
12.04781.051003.38671.0
3.25222.112003.27701.0
3.16893.163003.11351.0039
2.92784.214002.04851.3109
1.35925.265000.80441.0988
0.74726.326000.65710.9474
0.58427.377000.60790.9477
0.48318.428000.60830.9491
0.42599.479000.59160.8973
0.381710.5310000.60700.9147
0.33811.5811000.58730.8617
0.312312.6312000.59830.8844
0.28713.6813000.61460.8988
0.270614.7414000.60680.8754
0.250515.7915000.59960.8638
0.241216.8416000.61060.8481
0.217617.8917000.61520.8520
0.225518.9518000.61500.8540
0.21620.019000.61450.8512

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu102
  • Datasets 1.13.3
  • Tokenizers 0.10.3

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

Using it via the API

Call it like any OpenAI endpoint

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

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