Model reference · open weights
wav2vec2-large-xlsr-bengali is an open-weight audio or speech model from arijitx. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | arijitx |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
Fine-tuned facebook/wav2vec2-large-xlsr-53 Bengali using a subset of 40,000 utterances from Bengali ASR training data set containing ~196K utterances. Tested WER using ~4200 held out from training. When using this model, make sure that your speech input is sampled at 16kHz. Train Script can be Found at : train.py
The model can be used directly (without a language model) as follows:
import torch
import torchaudio
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
processor = Wav2Vec2Processor.from_pretrained("arijitx/wav2vec2-large-xlsr-bengali")
model = Wav2Vec2ForCTC.from_pretrained("arijitx/wav2vec2-large-xlsr-bengali")
# model = model.to("cuda")
resampler = torchaudio.transforms.Resample(TEST_AUDIO_SR, 16_000)
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch)
speech = resampler(speech_array).squeeze().numpy()
return speech
speech_array = speech_file_to_array_fn("test_file.wav")
inputs = processor(speech_array, sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values).logits
predicted_ids = torch.argmax(logits, dim=-1)
preds = processor.batch_decode(predicted_ids)[0]
print(preds.replace("[PAD]",""))
Test Result: WER on ~4200 utterance : 32.45 %
From the published model card. Full card on the HuggingFace links in the sidebar.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Speech Recognition | OpenSLR | Test WER | 32.450 |
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-bengali for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-bengali 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-large-xlsr-bengali" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.