Model reference · open weights
wav2vec2-indonesian-javanese-sundanese is an open-weight audio or speech model from indonesian-nlp, 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
Multilingual Speech Recognition for Indonesian Languages This is the model built for the project Multilingual Speech Recognition for Indonesian Languages. It is a fine-tuned facebook/wav2vec2-large-xlsr-53 model on the Indonesian Common Voice dataset, High-quality TTS data for Javanese - SLR41, and High-quality TTS data for Sundanese - SLR44 datasets. We also provide a live demo to test the model. 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: Evaluation The model can be evaluated as follows on the Indonesian test data of Common Voice. Test Result: 11.57 % Training The Common Voice train, validation, and ... datasets were used for training as well as ... and ... # TODO The script used for training can be found here (will be available soon)
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | indonesian-nlp |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 2.5M downloads / month |
| Likes | 15 |
| 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-indonesian-javanese-sundanese | — | BF16 | — | — | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | Common Voice 6.1 | Test WER | 4.056 |
| Automatic Speech Recognition | Common Voice 6.1 | Test CER | 1.472 |
| Automatic Speech Recognition | Common Voice 7 | Test WER | 4.492 |
| Automatic Speech Recognition | Common Voice 7 | Test CER | 1.577 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Test WER | 48.94 |
| Automatic Speech Recognition | Robust Speech Event - Test Data | Test WER | 68.95 |
Using it via the API
Once AxForge deploys wav2vec2-indonesian-javanese-sundanese for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-indonesian-javanese-sundanese 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-indonesian-javanese-sundanese" -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 ↗