First upload to the repo.

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12
+
+RUN apt-get update
+RUN apt-get install -y portaudio19-dev
+RUN apt-get install -y python3-pyaudio
+
+WORKDIR /home/user/app
+
+COPY ./requirements.txt ./requirements.txt
+
+RUN pip3 install -r requirements.txt
+
+CMD ["python", "main.py"]

main.py

@@ -0,0 +1,20 @@
+import gradio as gr
+import speech_recognition as sr
+
+def transcribe(filename):
+    r = sr.Recognizer()
+
+    with sr.AudioFile(filename) as source:
+        # listen for the data (load audio to memory)
+        audio_data = r.record(source)
+        # recognize (convert from speech to text)
+        text = r.recognize_google(audio_data)
+        
+        return text
+
+demo = gr.Interface(
+    transcribe,
+    [gr.Audio(type="filepath")],
+    "textbox",
+)
+demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,3 @@
+gradio==5.23.3
+PyAudio==0.2.14
+SpeechRecognition==3.14.2