model added

app.py

@@ -1,5 +1,5 @@
 import os
-#os.system("pip install nemo_toolkit['all']")
+os.system("pip install nemo_toolkit['all']")
 import pytube
 import gradio as gr
 
@@ -10,19 +10,21 @@ model = nemo_asr.models.EncDecCTCModel.from_pretrained(
     model_name="stt_en_quartznet15x5"
 )
 
-def speech_youtube(x):
-    data = pytube.YouTube(x)
-    audio = data.streams.get_audio_only()
-    text = model.transcribe(audio.download())
-    return text['text']
+# def speech_youtube(x):
+#     data = pytube.YouTube(x)
+#     audio = data.streams.get_audio_only()
+#     text = model.transcribe(audio.download())
+#     return text['text']
 
 def speech_file(x):
+    print(x)
     text = model.transcribe([f"{x}"])
+    print(text)
     return text
 
-def speech_record(x):
-    text = model.transcribe(x)
-    return text['text']
+# def speech_record(x):
+#     text = model.transcribe(x)
+#     return text['text']
 
 css = """
         .gradio-container {
@@ -113,23 +115,23 @@ with gr.Blocks(css = css) as demo:
     # Speech to Text Transcriptions!
     This demo uses the OpenAI whisper model which is trained on a large dataset of diverse audio that can perform multilingual speech recognition. The computation time is dependent on the length of the audio.
     """)
-    with gr.Tab("YouTube"):
-        audio_input = gr.Textbox(label="YouTube Link", placeholder="paste the youtube link here")
-        text_output = gr.Textbox(label="Transcription", show_label=False)
-        youtube_button = gr.Button("Transcribe")
+    # with gr.Tab("YouTube"):
+    #     audio_input = gr.Textbox(label="YouTube Link", placeholder="paste the youtube link here")
+    #     text_output = gr.Textbox(label="Transcription", show_label=False)
+    #     youtube_button = gr.Button("Transcribe")
     with gr.Tab("Audio File"):
         with gr.Row().style(equal_height=True):
             audio_input2 = gr.Audio(label="Audio File", type="filepath")
             text_output2 = gr.Textbox(label="Transcription", show_label=False)
         file_button = gr.Button("Transcribe")
-    with gr.Tab("Record"):
-        with gr.Row().style(equal_height=True):
-            audio_input3 = gr.Audio(label="Input Audio", source="microphone", type="filepath")
-            text_output3 = gr.Textbox(label="Transcription", show_label=False)
-        rec_button = gr.Button("Transcribe")
+    # with gr.Tab("Record"):
+    #     with gr.Row().style(equal_height=True):
+    #         audio_input3 = gr.Audio(label="Input Audio", source="microphone", type="filepath")
+    #         text_output3 = gr.Textbox(label="Transcription", show_label=False)
+    #     rec_button = gr.Button("Transcribe")
     gr.HTML('''
         <div class="footer">
-                    <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> - Gradio Demo by 👩🏽‍🦱 <a href="https://www.linkedin.com/in/oayodeji/" style="text-decoration: underline;" target="_blank">Wvle</a>
+                    <p></a>
                     </p>
         </div>
         ''')