Update app.py

app.py

@@ -1,6 +1,3 @@
-# Install required packages
-#!pip install torch torchaudio transformers pydub gradio
-
 import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from pydub import AudioSegment
@@ -14,9 +11,14 @@ 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
+# Create pipeline with correct parameter
 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
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    device=0 if torch.cuda.is_available() else -1,
+    generate_kwargs={"input_features": None},  # Ensure correct input handling
 )
 
 # Convert audio to WAV format
@@ -46,7 +48,7 @@ def transcribe_long_audio(audio_path):
     transcription = ""
     
     for chunk in chunk_paths:
-        result = whisper_pipe(chunk)
+        result = whisper_pipe(chunk)  # No longer uses deprecated `inputs`
         transcription += result["text"] + "\n"
         os.remove(chunk)  # Remove processed chunk
     
@@ -67,4 +69,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()