Update app.py

app.py

@@ -2,17 +2,6 @@ import gradio as gr
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import torch
 import torchaudio
-import subprocess
-import sys
-
-# Function to install required packages
-def install(package):
-    subprocess.check_call([sys.executable, "-m", "pip", "install", package])
-
-install("transformers")
-install("torch")
-install("torchaudio")
-install("gradio")
 
 # Load pre-trained model and processor
 model_name = "facebook/wav2vec2-base-960h"
@@ -21,8 +10,11 @@ model = Wav2Vec2ForCTC.from_pretrained(model_name)
 
 def speech_to_text(audio):
     try:
+        if audio is None:
+            return "No audio file provided."
+
         # Load audio file
-        waveform, rate = torchaudio.load(audio.name)
+        waveform, rate = torchaudio.load(audio)
         
         # Ensure the audio is mono
         if waveform.shape[0] > 1:
@@ -50,8 +42,8 @@ def speech_to_text(audio):
 # Create Gradio interface
 iface = gr.Interface(
     fn=speech_to_text,
-    inputs=gr.Audio(type="filepath"),
-    outputs="text",
+    inputs=gr.Audio(type="filepath", label="Input Audio"),
+    outputs=gr.Textbox(label="Transcription"),
     live=True,
     title="Speech to Text",
     description="Speak into your microphone and get the transcribed text."