Upload 3 files

README.md

@@ -1,7 +1,7 @@
 ---
-title: Whisper Offline
-emoji: 🐠
-colorFrom: pink
+title: Whisper-offline
+emoji: 📉
+colorFrom: red
 colorTo: green
 sdk: gradio
 sdk_version: 3.12.0
@@ -11,3 +11,5 @@ license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+

app.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Dec  8 17:37:44 2022
+
+@author: Kenneth
+"""
+
+from transformers import pipeline
+import gradio as gr
+from pytube import YouTube
+from datasets import Dataset, Audio
+import os
+from moviepy.editor import AudioFileClip
+import time
+
+pipe = pipeline(model="YuhangDeng123/whisper-small-hi")  # change to "your-username/the-name-you-picked"
+
+def transcribe(audio):
+    text = pipe(audio)["text"]
+    return text
+
+with gr.Blocks() as demo:
+    gr.Markdown("Whisper-Small Cantonese Recognition")
+    with gr.Row():
+        with gr.TabItem("Upload An Audio File"):
+            upload_file = gr.Audio(source="upload", type="filepath",label="Upload An Audio File")
+            upload_button = gr.Button("Submit")
+            upload_outputs = [gr.Textbox(label="Recognized result from uploaded audio file"),]
+    with gr.Row():
+        with gr.TabItem("Record from Microphone"):
+            record_file = gr.Audio(source="microphone", type="filepath",label="Record from microphone")
+            record_button = gr.Button("Submit")
+            record_outputs = [gr.Textbox(label="Recognized result from Microphone"),]  
+    upload_button.click(
+        fn=transcribe,
+        inputs=upload_file,
+        outputs=upload_outputs,
+    )
+    
+    record_button.click(
+        fn=transcribe,
+        inputs=record_file,
+        outputs=record_outputs,
+    )    
+demo.launch()

requirements.txt

@@ -0,0 +1,9 @@
+gradio
+transformers
+torch
+git+https://github.com/pytube/pytube
+datasets
+torchaudio
+librosa
+jiwer
+moviepy