Update README.md

README.md

@@ -14,5 +14,54 @@ library_name: transformers
 this model trained on validation segment of data for one epoch with 0.05 loss and tested on test segment of data with 0.07 loss
 
 how to use the model in colab:
+    # Install required packages
+    !pip install torch torchaudio transformers pydub google-colab
+    
+    import torch
+    from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+    from pydub import AudioSegment
+    import os
+    from google.colab import files
+    
+    # Load the model and processor
+    model_id = "hackergeek98/tinyyyy_whisper"
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    
+    model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device)
+    processor = AutoProcessor.from_pretrained(model_id)
+    
+    # Create pipeline
+    whisper_pipe = pipeline(
+        "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, device=0 if torch.cuda.is_available() else -1
+    )
+    
+    # Convert audio to WAV format
+    def convert_to_wav(audio_path):
+        audio = AudioSegment.from_file(audio_path)
+        wav_path = "converted_audio.wav"
+        audio.export(wav_path, format="wav")
+        return wav_path
+    
+    # Transcribe an audio file and save as text
+    def transcribe(audio_path):
+        wav_path = convert_to_wav(audio_path)
+        result = whisper_pipe(wav_path)
+        os.remove(wav_path)  # Cleanup temporary file
+        
+        # Save transcription to a text file
+        text_path = "transcription.txt"
+        with open(text_path, "w") as f:
+            f.write(result["text"])
+        
+        return text_path
+    
+    # Upload and process audio in Colab
+    uploaded = files.upload()
+    audio_file = list(uploaded.keys())[0]
+    transcription_file = transcribe(audio_file)
+    
+    # Download the transcription file
+    files.download(transcription_file)
+