Init

app.py

@@ -0,0 +1,36 @@
+import whisper
+import gradio as gr
+
+model = whisper.load_model("tiny")
+
+def transcribe(audio):
+    
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions(fp16 = False, language="en")
+    result = whisper.decode(model, mel, options)
+    return result.text
+    
+    
+ 
+gr.Interface(
+    title = 'EN Whisper ASR With Auto Punctuation', 
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath")
+    ],
+    outputs=[
+        "textbox"
+    ]
+).launch()

requirements.txt

@@ -0,0 +1 @@
+git+https://github.com/openai/whisper.git