|
--- |
|
license: apache-2.0 |
|
language: |
|
- bn |
|
base_model: |
|
- openai/whisper-small |
|
|
|
pipeline_tag: automatic-speech-recognition |
|
|
|
--- |
|
BengaliRegionalASR trained on bengali regional dialact dataset. |
|
|
|
# Try the model |
|
```py |
|
import os |
|
import librosa |
|
import torch, torchaudio |
|
import numpy as np |
|
from transformers import WhisperTokenizer ,WhisperProcessor, WhisperFeatureExtractor, WhisperForConditionalGeneration |
|
model_path_ = "sha1779/BengaliRegionalASR" |
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') |
|
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) |
|
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="bengali", task="transcribe") |
|
|
|
mp3_path = "https://huggingface.co/sha1779/BengaliRegionalASR/resolve/main/Mp3/common_voice_bn_31617644.mp3" |
|
speech_array, sampling_rate = librosa.load(mp3_path, sr=16000) |
|
|
|
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 |
|
|
|
predicted_ids = model.generate(inputs=input_features.to(device))[0] |
|
|
|
transcription = processor.decode(predicted_ids, skip_special_tokens=True) |
|
|
|
print(transcription) |
|
|
|
``` |
|
|
|
# Evaluation |
|
Word Error Rate 0.65 % |
|
|
|
|
|
|
|
|
