Update README.md

README.md

@@ -40,6 +40,53 @@ print(transcription)
 
 ```
 
+## For larger audio , more than 30s
+```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/valid_barishal%20(1).wav"
+
+
+speech_array, sampling_rate = librosa.load(mp3_path, sr=16000)
+
+# Split audio into 30-second chunks with 5-second overlap
+chunk_duration = 30  # seconds
+overlap = 5  # seconds
+chunk_size = int(chunk_duration * sampling_rate)
+overlap_size = int(overlap * sampling_rate)
+
+chunks = []
+for start in range(0, len(speech_array), chunk_size - overlap_size):
+    end = start + chunk_size
+    chunk = speech_array[start:end]
+    chunks.append(chunk)
+
+# Process each chunk
+transcriptions = []
+for i, chunk in enumerate(chunks):
+     
+    # Resample and extract features
+    chunk = librosa.resample(np.asarray(chunk), orig_sr=sampling_rate, target_sr=16000)
+    input_features = feature_extractor(chunk, sampling_rate=16000, return_tensors="pt").input_features
+    
+    # Generate transcription
+    predicted_ids = model.generate(inputs=input_features.to(device))[0]
+    transcription = processor.decode(predicted_ids, skip_special_tokens=True)
+    print(transcription,end=" ")
+
+``` 
+
 # Evaluation
 Word Error Rate 0.65 %