Model reference · open weights

BanglaASR

Available as managed deployment Audio bangla-speech-processing Speech→text 1 variants 16k dl/mo

BanglaASR is an open-weight audio or speech model from bangla-speech-processing. 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 bybangla-speech-processing
TypeAudio & music
TaskSpeech→text
Parameters (lead)242M
Runs withtransformers
Released2023-06-22
Popularity16k downloads / month
LicenceOpen weights

About

What BanglaASR is

Bangla ASR model which was trained Bangla Mozilla Common Voice Dataset. This is Fine-tuning Whisper model using Bangla mozilla common voice dataset. For training this model used 40k training and 7k Validation of around 400 hours of data. We trained 12000 steps and get word error rate 4.58%. This model was whisper small[244 M] variant model.

Read the full model card

import os
import librosa
import torch
import torchaudio
import numpy as np

from transformers import WhisperTokenizer
from transformers import WhisperProcessor
from transformers import WhisperFeatureExtractor
from transformers import WhisperForConditionalGeneration

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

mp3_path = "https://huggingface.co/bangla-speech-processing/BanglaASR/resolve/main/mp3/common_voice_bn_31515636.mp3"

model_path = "bangla-speech-processing/BanglaASR"

feature_extractor = WhisperFeatureExtractor.from_pretrained(model_path)
tokenizer = WhisperTokenizer.from_pretrained(model_path)
processor = WhisperProcessor.from_pretrained(model_path)
model = WhisperForConditionalGeneration.from_pretrained(model_path).to(device)

speech_array, sampling_rate = torchaudio.load(mp3_path, format="mp3")
speech_array = speech_array[0].numpy()
speech_array = librosa.resample(np.asarray(speech_array), orig_sr=sampling_rate, target_sr=16000)
input_features = feature_extractor(speech_array, sampling_rate=16000, return_tensors="pt").input_features

# batch = processor.feature_extractor.pad(input_features, return_tensors="pt")
predicted_ids = model.generate(inputs=input_features.to(device))[0]

transcription = processor.decode(predicted_ids, skip_special_tokens=True)

print(transcription)

Dataset

Used Mozilla common voice dataset around 400 hours data both training[40k] and validation[7k] mp3 samples. For more information about dataser please click here

Training Model Information

SizeLayersWidthHeadsParametersBangla-onlyTraining Status
tiny4384639 MXX
base6512874 MXX
small1276812244 M
medium24102416769 MXX
large321280201550 MXX

Evaluation

Word Error Rate 4.58 %

For More please check the github

@misc{BanglaASR ,
  title={Transformer Based Whisper Bangla ASR Model},
  author={Md Saiful Islam},
  howpublished={},
  year={2023}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys banglaasr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (banglaasr 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="banglaasr" -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.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms