app.py

app.py

@@ -0,0 +1,20 @@
+from transformers import pipeline
+import gradio as gr
+
+pipe = pipeline(model="asif00/whisper-bangla")
+
+
+def transcribe(audio):
+    text = pipe(audio)["text"]
+    return text
+
+
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(sources="microphone", type="filepath"),
+    outputs="text",
+    title="Whisper Bangla",
+    description="Realtime demo for Bengali speech recognition using a fine-tuned Whisper small model.",
+)
+
+iface.launch()

flagged/log.csv

@@ -0,0 +1,2 @@
+audio,output,flag,username,timestamp
+flagged\audio\3078fa84e061327e99b6\audio.wav,আফনি কেমন আসেন।,,,2024-06-04 01:02:36.210092