Model reference · open weights
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.
About
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
| Maker | Harveenchadha |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 1.1M downloads / month |
| Likes | 4 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| vakyansh-wav2vec2-tamil-tam-250 | — | BF16 | — | — | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Speech Recognition | Common Voice ta | Test WER | 53.64 |
Using it via the API
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
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗