Model reference · open weights
wav2vec2-conformer-rope-large-960h-ft is an open-weight audio or speech model from facebook, 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-Conformer-Large-960h with Rotary Position Embeddings Wav2Vec2 Conformer with rotary position embeddings, pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Paper: fairseq S2T: Fast Speech-to-Text Modeling with fairseq Authors: Changhan Wang, Yun Tang, Xutai Ma, Anne Wu, Sravya Popuri, Dmytro Okhonko, Juan Pino The results of Wav2Vec2-Conformer can be found in Table 3 and Table 4 of the official paper. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20. Usage To transcribe audio files the model can be used as a standalone acoustic model as follows: Evaluation This code snippet shows how to evaluate facebook/wav2vec2-conformer-rope-large-960h-ft on LibriSpeech's "clean" and "other" test data. Result (WER):
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 593M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-04-18 |
| Popularity | 202k downloads / month |
| Likes | 11 |
| 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-conformer-rope-large-960h-ft | 593M | BF16 | ~1.4 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | LibriSpeech (clean) | Test WER | 1.96 |
| Automatic Speech Recognition | LibriSpeech (other) | Test WER | 3.98 |
Using it via the API
Once AxForge deploys wav2vec2-conformer-rope-large-960h-ft for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-conformer-rope-large-960h-ft 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-conformer-rope-large-960h-ft" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗