Create app.py

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+import os
+import wave
+import tempfile
+import numpy as np
+
+# Global variables to store file and line index
+file_index = 0
+line_index = 0
+lines = []
+
+# Function to read lines from a file
+def read_lines_from_file(file_path):
+    global lines
+    with open(file_path, 'r') as file:
+        lines = file.readlines()
+
+# Function to save audio to a WAV file
+def save_audio_to_file(audio):
+    global file_index, line_index, lines
+    
+    sample_rate, data = audio  # audio is a tuple (sample_rate, data)
+    
+    # Save the audio data as a WAV file in a temporary location
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        with wave.open(tmp_file.name, 'wb') as wav_file:
+            wav_file.setnchannels(1)  # Mono audio
+            wav_file.setsampwidth(2)  # 2 bytes per sample (16-bit PCM)
+            wav_file.setframerate(sample_rate)
+            wav_file.writeframes(data.tobytes())
+        
+        # Return the path to the saved WAV file
+        return tmp_file.name
+
+# Gradio interface function
+def audio_capture_interface():
+    global file_index, line_index, lines
+    
+    # Initial file to read
+    files = os.listdir('./audio_samples')
+    read_lines_from_file(os.path.join('./audio_samples', files[file_index]))
+
+    # Define the interface components
+    audio_input = gr.Audio(source="microphone", type="numpy", label="Speak and click submit")
+    output_text = gr.Textbox(label="Status", placeholder="Status will appear here")
+
+    # Function to capture and process the audio input
+    def process_audio(audio):
+        global line_index, lines
+        
+        try:
+            file_path = save_audio_to_file(audio)
+            return f"Audio saved to {file_path}"
+        except Exception as e:
+            return f"Error saving audio: {str(e)}"
+
+    # Function to handle navigation buttons
+    def navigate_lines(button):
+        global line_index, lines
+        
+        if button == 'forward':
+            line_index = min(line_index + 1, len(lines) - 1)
+        elif button == 'previous':
+            line_index = max(line_index - 1, 0)
+        
+        output_text.value = lines[line_index]
+
+    # Create the Gradio interface
+    iface = gr.Interface(
+        fn=process_audio,
+        inputs=audio_input,
+        outputs=output_text,
+        live=True,
+        title="Audio Capture and Playback",
+        description="Speak into the microphone and click submit to save audio. Navigate through lines using buttons below.",
+        theme="compact",
+        layout="vertical",
+        examples=[["Start recording audio."]]
+    )
+
+    # Add navigation buttons
+    iface.add_button("Previous", lambda: navigate_lines('previous'))
+    iface.add_button("Forward", lambda: navigate_lines('forward'))
+
+    return iface
+
+# Launch the interface
+iface = audio_capture_interface()
+iface.launch()