metadata
language:
- bn
tags:
- whisper
- automatic-speech-recognition
- bengali
license: apache-2.0
metrics:
- wer
pipeline_tag: automatic-speech-recognition
Whisper Small Bengali
This is a fine-tuned Whisper Small model for Bengali (Bangla) speech recognition.
Model Details
- Base Model: openai/whisper-small
- Language: Bengali (bn)
- Training Steps: 2000
- Final Training Loss: N/A
Usage
from transformers import WhisperProcessor, WhisperForConditionalGeneration, WhisperTokenizer
import torch
import librosa
# Load model and tokenizer
model = WhisperForConditionalGeneration.from_pretrained("Noobbbbb/whisper-small-bn")
tokenizer = WhisperTokenizer.from_pretrained("Noobbbbb/whisper-small-bn")
processor = WhisperProcessor.from_pretrained("Noobbbbb/whisper-small-bn")
# Load audio (must be 16kHz)
audio, sr = librosa.load("audio.wav", sr=16000)
# Extract features
input_features = processor.feature_extractor(
audio,
sampling_rate=16000,
return_tensors="pt"
).input_features
# Generate transcription
with torch.no_grad():
generated_ids = model.generate(input_features, max_length=448)
# Decode
transcription = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
print(transcription)
Training Details
- Training Data: openslr37
- Language: Bengali (bn)
- Training Steps: 2000
- Batch Size: 4
- Learning Rate: 1e-05
- Optimizer: AdamW
- eval_wer: 0.3080158337456705
Limitations
- Optimized for Bengali speech only
- Works best with clear audio at 16kHz sampling rate
- May not perform well on heavily accented or noisy audio
Acknowledgments
Based on OpenAI's Whisper model: https://github.com/openai/whisper