Model reference · open weights
wav2vec2-xlsr-nepali is an open-weight audio or speech model from gagan3012, 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
Wav2Vec2-Large-XLSR-53-Nepali Fine-tuned facebook/wav2vec2-large-xlsr-53 on Nepali using the Common Voice, and OpenSLR ne. When using this model, make sure that your speech input is sampled at 16kHz. Usage The model can be used directly (without a language model) as follows: Result Prediction: ['पारानाको ब्राजिली राज्यमा रहेको राजधानी', 'देवराज जोशी त्रिभुवन विश्वविद्यालयबाट शिक्षाशास्त्रमा स्नातक हुनुहुन्छ'] Reference: ['पारानाको ब्राजिली राज्यमा रहेको राजधानी', 'देवराज जोशी त्रिभुवन विश्वविद्यालयबाट शिक्षाशास्त्रमा स्नातक हुनुहुन्छ'] Evaluation The model can be evaluated as follows on the {language} test data of Common Voice. # TODO: replace #TODO: replace language with your {language}, e.g. French Test Result: 05.97 % Training The script used for training can be found here
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | gagan3012 |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 771k downloads / month |
| Likes | 8 |
| 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 |
|---|---|---|---|---|---|
| wav2vec2-xlsr-nepali | — | BF16 | — | — | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Speech Recognition | OpenSLR ne | Test WER | 5.97 |
Using it via the API
Once AxForge deploys wav2vec2-xlsr-nepali for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-xlsr-nepali 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-xlsr-nepali" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗