Update app.py

app.py

@@ -2,17 +2,12 @@ import gradio as gr
 from transformers import pipeline
 import librosa
 
-# Initialize the model
+# Initialize the ASR model
 asr_model = pipeline("automatic-speech-recognition", model="openai/whisper-small")
 
-def transcribe(audio_data):
-    # librosa expects a file path, but gradio passes a tuple (file name, file object)
-    # If the audio comes from a microphone, it's in the second position of the tuple
-    if isinstance(audio_data, tuple):
-        audio_data = audio_data[1]
-
+def transcribe(file_path):
     # Load the audio file with librosa
-    data, samplerate = librosa.load(audio_data, sr=None)
+    data, samplerate = librosa.load(file_path, sr=None)
     # Pass the audio data to the model for transcription
     transcription = asr_model(data, sampling_rate=samplerate)
     return transcription["text"]
@@ -20,8 +15,9 @@ def transcribe(audio_data):
 # Create the Gradio interface
 iface = gr.Interface(
     fn=transcribe,
-    inputs=gr.Audio(type="file", label="Record or Upload Audio"),
+    inputs=gr.Audio(type="filepath", label="Record or Upload Audio"),
     outputs="text"
 )
 
+# Launch the interface
 iface.launch()