Update app.py

app.py

@@ -14,8 +14,73 @@ whisper_model = whisper.load_model("medium")
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-def greet(name):
-    return "Hello " + name + "!!"
+def transcribe(audio):
+    
+    print("""
+    —
+    Sending audio to Whisper ...
+    —
+    """)
+    
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+    
+    mel = whisper.log_mel_spectrogram(audio).to(whisper_model.device)
+    
+    _, probs = whisper_model.detect_language(mel)
+    
+    transcript_options = whisper.DecodingOptions(task="transcribe", fp16 = False)
+    translate_options = whisper.DecodingOptions(task="translate", fp16 = False)
+    
+    transcription = whisper.decode(whisper_model, mel, transcript_options)
+    translation = whisper.decode(whisper_model, mel, translate_options)
+    
+    print("Language Spoken: " + transcription.language)
+    print("Transcript: " + transcription.text)  
+    print("Translated: " + translation.text)
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+ 
+    return transcription.text
+
+def transcribe_upload(audio):
+    return transcribe(audio)
+
+def transcribe_yt(link):
+    yt = YouTube(link)
+    path = yt.streams.filter(only_audio=True)[0].download(filename="audio.mp3")
+    return transcribe(path)
+
+with gr.Blocks(css = css) as demo:
+    gr.Markdown("""
+                ## Multi-lingual Transcript Generator
+            """)
+    gr.HTML('''
+     <p style="margin-bottom: 10px">
+                Save Transcripts of videos as PDF with the help of Whisper, which is a general-purpose speech recognition model released by OpenAI that can perform multilingual speech recognition as well as speech translation and language identification. 
+              </p>
+              ''')
+    with gr.Column():
+            #gr.Markdown(""" ### Record audio """)
+        with gr.Tab("Youtube Link"):
+            yt_input = gr.Textbox(label = 'Youtube Link')
+            transcribe_audio_yt = gr.Button('Transcribe')
+        
+        with gr.Tab("Upload Podcast as File"):
+            audio_input_u = gr.Audio(label = 'Upload Audio',source="upload",type="filepath")
+            transcribe_audio_u = gr.Button('Transcribe')
+
+        with gr.Row():
+            transcript_output = gr.Textbox(label="Transcription in the language spoken", lines = 20)
+            summary_output = gr.Textbox(label = "English Summary", lines = 10)
+    
+    transcribe_audio_yt.click(transcribe_yt, inputs = yt_input, outputs = [transcript_output, summary_output])
+    transcribe_audio_u.click(transcribe_upload, inputs = audio_input_u, outputs = [transcript_output,summary_output])   
+    gr.HTML('''
+        <div class="footer">
+                    <p>Whisper Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a>
+                    </p>
+        </div>
+        ''')
+        
+demo.queue()    
+demo.launch()