Model reference · open weights

vakyansh-wav2vec2-tamil-tam-250

vakyansh-wav2vec2-tamil-tam-250 is an open-weight audio or speech model from Harveenchadha, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio Harveenchadha 1 variants 1.1M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What vakyansh-wav2vec2-tamil-tam-250 is

Pretrained Model Fine-tuned on Multilingual Pretrained Model CLSRIL-23. The original fairseq checkpoint is present here. When using this model, make sure that your speech input is sampled at 16kHz. Note: The result from this model is without a language model so you may witness a higher WER in some cases. Dataset This model was trained on 4200 hours of Hindi Labelled Data. The labelled data is not present in public domain as of now. Training Script Models were trained using experimental platform setup by Vakyansh team at Ekstep. Here is the training repository. In case you want to explore training logs on wandb they are here. Colab Demo Usage The model can be used directly (without a language model) as follows: Evaluation The model can be evaluated as follows on the hindi test data of Common Voice. Test Result: 53.64 % Colab Evaluation Credits Thanks to Ekstep Foundation for making this possible. The vakyansh team will be open sourcing speech models in all the Indic Languages.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerHarveenchadha
TypeAudio & music
Variants1
Runs withtransformers
Released2022-03-02
Popularity1.1M downloads / month
Likes4
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
vakyansh-wav2vec2-tamil-tam-250BF16Weights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Speech RecognitionCommon Voice taTest WER53.64

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys vakyansh-wav2vec2-tamil-tam-250 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vakyansh-wav2vec2-tamil-tam-250 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="vakyansh-wav2vec2-tamil-tam-250" -F file=@audio.mp3

Details

Languages, data & research

Languages

ta

Tags

transformers pytorch wav2vec2 automatic-speech-recognition audio speech ta model-index endpoints_compatible deploy:azure

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want vakyansh-wav2vec2-tamil-tam-250 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

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