initial commit

app.py

@@ -1,7 +1,32 @@
 import gradio as gr
+from transformers import pipeline
+import numpy as np
 
 def greet(name):
     return "Hello " + name + "!!"
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")
 iface.launch()
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+
+def transcribe(stream, new_chunk):
+    sr, y = new_chunk
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    if stream is not None:
+        stream = np.concatenate([stream, y])
+    else:
+        stream = y
+    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
+
+
+demo = gr.Interface(
+    transcribe,
+    ["state", gr.Audio(sources=["microphone"], streaming=True)],
+    ["state", "text"],
+    live=True,
+)
+
+demo.launch()
+