Initial demo

README.md

@@ -1,6 +1,6 @@
 ---
 title: Whisper Medium Mn
-emoji: 📉
+emoji: 🌍
 colorFrom: blue
 colorTo: pink
 sdk: gradio
@@ -9,4 +9,4 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,19 @@
+from transformers import pipeline
+import gradio as gr
+
+# Specify the task explicitly
+pipe = pipeline(task="automatic-speech-recognition", model="erkhem-gantulga/whisper-medium-mn")
+
+def transcribe(audio):
+    text = pipe(audio)["text"]
+    return text
+
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(sources=["upload", "microphone"], type="filepath"),
+    outputs="text",
+    title="Whisper Medium Mongolian",
+    description="Realtime demo for Mongolian speech recognition using a fine-tuned Whisper medium model.",
+)
+
+iface.launch()

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,3 @@
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch
+transformers