Init

app.py

@@ -0,0 +1,22 @@
+from faster_whisper import WhisperModel
+import gradio as gr
+
+model_size = "small"
+
+# Run on GPU with FP16
+model = WhisperModel(model_size, device="cpu", compute_type="int8")
+
+def transcribe(audio):
+    segments, _ = model.transcribe(audio, beam_size=5)    
+    return "".join([segment.text for segment in segments])
+ 
+gr.Interface(
+    title = 'Fast Whisper for Speech Recognition', 
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath")
+    ],
+    outputs=[
+        "textbox"
+    ]
+).launch()

requirements.txt

@@ -0,0 +1 @@
+faster-whisper