Model reference · open weights
filipino-wav2vec2-l-xls-r-official is an open-weight audio or speech model from Khalsuu, 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
should probably proofread and complete it, then remove this comment. -- filipino-wav2vec2-l-xls-r-300m-official This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the filipinovoice dataset. It achieves the following results on the evaluation set: - Loss: 0.4672 - Wer: 0.2922 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: - learningrate: 0.0003 - trainbatchsize: 8 - evalbatchsize: 8 - seed: 42 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: linear - lrschedulerwarmupsteps: 500 - numepochs: 30 - mixedprecisiontraining: Native AMP Training results Framework versions - Transformers 4.11.3 - Pytorch 1.10.0+cu113 - Datasets 1.18.3 - Tokenizers 0.10.3
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Khalsuu |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-05-13 |
| Popularity | 1.4M downloads / month |
| Likes | 2 |
| 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 |
|---|---|---|---|---|---|
| filipino-wav2vec2-l-xls-r-300m-official | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys filipino-wav2vec2-l-xls-r-official for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (filipino-wav2vec2-l-xls-r-official 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="filipino-wav2vec2-l-xls-r-official" -F file=@audio.mp3
Details
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 ↗