Create asr_transcription.ipynb

asr_transcription.ipynb

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+transcriber = pipeline('automatic-speech-recognition', model='openai/whisper-base')
+
+def transcribe(audio):
+    sr, y = audio
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    return transcriber({'sampling_rate': sr, 'raw': y})['text']
+
+
+demo = gr.Interface(
+    fn = transcribe,
+    inputs = gr.Audio(sources=['microphone']),
+    outputs = 'text',
+)
+
+demo.launch()