Update app.py

app.py

@@ -32,25 +32,6 @@ def transcribe(microphone, file_upload):
     return warn_output + text
 
 
-# def _return_yt_html_embed(yt_url):
-#     video_id = yt_url.split("?v=")[-1]
-#     HTML_str = (
-#         f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
-#         " </center>"
-#     )
-#     return HTML_str
-
-
-# def yt_transcribe(yt_url):
-#     yt = pt.YouTube(yt_url)
-#     html_embed_str = _return_yt_html_embed(yt_url)
-#     stream = yt.streams.filter(only_audio=True)[0]
-#     stream.download(filename="audio.mp3")
-
-#     text = pipe("audio.mp3")["text"]
-
-#     return html_embed_str, text
-
 def rt_transcribe(audio, state=""):
     time.sleep(2)
     text = p(audio)["text"]
@@ -60,7 +41,7 @@ def rt_transcribe(audio, state=""):
 
 demo = gr.Blocks()
 
-examples=[["examples/example1.mp3"], ["examples/example2.mp3"]]
+examples=[["examples/example1.mp3"], ["examples/example2.mp3"],["examples/example3.mp3"]]
 
 description = """
 <p>
@@ -69,10 +50,14 @@ Welcome to the HindiSpeechPro, a cutting-edge interface powered by a fine-tuned
 </center>
 </p>
 <center>
-<img src="https://huggingface.co/spaces/kingabzpro/real-time-Urdu-ASR/resolve/main/Images/cover.jpg" alt="logo" width="550"/>
+<img src="https://huggingface.co/spaces/SakshiRathi77/SakshiRathi77-Wav2Vec2-hi-kagglex/blob/main/Images/Hindi-Speech-Voice-Recognition-Tool.jpg" alt="logo" width="550"/>
 </center>
 """
 
+
+css='div {margin-left: auto; margin-right: auto; width: 100%;\
+            background-image: url("https://huggingface.co/spaces/SakshiRathi77/SakshiRathi77-Wav2Vec2-hi-kagglex/blob/main/Images/image-bg.jpg"); repeat 0 0;}')
+
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
@@ -85,7 +70,26 @@ mf_transcribe = gr.Interface(
     description= description ,
     allow_flagging="never",
     examples=examples,
-).launch(share=True )
+    css=css,
+)
+
+rt_transcribe = gr.Interface(
+    fn=rt_transcribe,
+    inputs=[
+        gr.Audio(source="microphone", type="filepath", streaming=True), 
+        "state"
+    ],
+    outputs=[ "textbox",
+        "state"],
+    theme='EveryPizza/Cartoony-Gradio-Theme',
+    title="HindiSpeechPro: WAV2VEC-Powered ASR Interface",
+    description= description ,
+    allow_flagging="never",
+    live=True
+)
+
 
+with demo:
+    gr.TabbedInterface([mf_transcribe, rt_transcribe], ["Transcribe Audio", "Transcribe Realtime Voice"])
 
-gr.Interface.load("models/SakshiRathi77/wav2vec2-large-xlsr-300m-hi-kagglex").launch()
+demo.launch(share=True)