GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bangla-speech-processing
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
bangla-speech-processing
Model Tree
Input Modalities
Output Modalities
Supported Functionality
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.
py
import osimport librosaimport torchimport torchaudioimport numpy as np from transformers import WhisperTokenizerfrom transformers import WhisperProcessorfrom transformers import WhisperFeatureExtractorfrom 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)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
| Size | Layers | Width | Heads | Parameters | Bangla-only | Training Status |
|---|---|---|---|---|---|---|
| tiny | 4 | 384 | 6 | 39 M | X | X |
| base | 6 | 512 | 8 | 74 M | X | X |
| small | 12 | 768 | 12 | 244 M | ✓ | ✓ |
| medium | 24 |
Word Error Rate 4.58 %
For More please check the github
text
@misc{BanglaASR , title={Transformer Based Whisper Bangla ASR Model}, author={Md Saiful Islam}, howpublished={}, year={2023}}import osimport librosaimport torchimport torchaudioimport numpy as np from transformers import WhisperTokenizerfrom transformers import WhisperProcessorfrom transformers import WhisperFeatureExtractorfrom 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)| 1024 |
| 16 |
| 769 M |
| X |
| X |
| large | 32 | 1280 | 20 | 1550 M | X | X |