Upload app.py

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import speech_recognition as sr
+from pydub import AudioSegment
+
+def transcribe_audio(audio_file_path, input_language):
+    # Add silence padding
+    audio = AudioSegment.from_file(audio_file_path, format="wav")
+    two_sec_silence = AudioSegment.silent(duration=2500)
+    audio = two_sec_silence + audio + two_sec_silence
+    audio.export("stt_audio.wav", format="wav")
+    file_path2 = "stt_audio.wav"
+
+    recognizer = sr.Recognizer()
+    try:
+        with sr.AudioFile(file_path2) as source:
+            recognizer.adjust_for_ambient_noise(source)
+            audio_data = recognizer.record(source)
+
+        # Google API call
+        text = recognizer.recognize_google(audio_data, language=input_language)
+        return text
+
+    except sr.UnknownValueError:
+        return "Could not understand the audio"
+    except sr.RequestError as e:
+        return f"Could not request results; {e}"
+
+# Gradio interface
+iface = gr.Interface(
+    fn=transcribe_audio,
+    inputs=[
+        gr.Audio(source="upload", type="filepath", label="Upload Audio (.wav)"),
+        gr.Textbox(label="Language code (e.g., en-US, fa-IR)")
+    ],
+    outputs="text",
+    title="Google Speech-to-Text",
+    description="Upload a WAV file and get transcription using Google STT API."
+)
+
+iface.launch()