Update app.py

app.py

@@ -104,7 +104,7 @@ def Transcribe(audio="temp_audio.wav"):
     RemoveAllFiles()
     return (t_text, ({ "data": [{"speaker": speaker, "text": text} for speaker, text in conversation]}))
 
-def AudioTranscribe(audio, retries=5):
+def AudioTranscribe(NumberOfSpeakers=None, SpeakerNames="", audio, retries=5):
     if retries:
         try:
             subprocess.call(['ffmpeg', '-i', audio,'temp_audio.wav'])
@@ -117,7 +117,7 @@ def AudioTranscribe(audio, retries=5):
     else:
         raise gr.Error("There is some issue ith Audio Transcriber. Please try again later!")
 
-def VideoTranscribe(video, retries=5):
+def VideoTranscribe(NumberOfSpeakers=None, SpeakerNames="", video, retries=5):
     if retries:
         try:
             command = f"ffmpeg -i {video} -ab 160k -ac 2 -ar 44100 -vn temp_audio.wav"
@@ -132,7 +132,7 @@ def VideoTranscribe(video, retries=5):
         raise gr.Error("There is some issue ith Video Transcriber. Please try again later!")
     return Transcribe()
 
-def YoutubeTranscribe(URL, retries = 5):
+def YoutubeTranscribe(NumberOfSpeakers=None, SpeakerNames="", URL, retries = 5):
     if retries:
         if "youtu" not in URL.lower():
             raise gr.Error(f"{URL} is not a valid youtube URL.")
@@ -160,17 +160,17 @@ def YoutubeTranscribe(URL, retries = 5):
  
 ut = gr.Interface(
     fn=YoutubeTranscribe,
-    inputs=[gr.Number(label="Number of Speakers", placeholder="2"), gr.Textbox(label="Name of the Speakers (ordered by the time they speak and seperated by comma)", placeholder="Speaker 1, Speaker 2"), gr.Textbox(label="Youtube Link", placeholder="https://www.youtube.com/watch?v=GECcjrYHH8w"),],
+    inputs=[gr.Number(label="Number of Speakers", placeholder="2"), gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2"), gr.Textbox(label="Youtube Link", placeholder="https://www.youtube.com/watch?v=GECcjrYHH8w"),],
     outputs=[gr.Textbox(label="Transcribed Text", lines=15), gr.JSON(label="Transcribed JSON")]
 )
 vt = gr.Interface(
     fn=VideoTranscribe,
-    inputs='video',
+    inputs=[gr.Number(label="Number of Speakers", placeholder="2"), gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2"), 'video'],
     outputs=[gr.Textbox(label="Transcribed Text", lines=15), gr.JSON(label="Transcribed JSON")]
 )
 at = gr.Interface(
     fn=AudioTranscribe,
-    inputs='audio',
+    inputs=[gr.Number(label="Number of Speakers", placeholder="2"), gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2"), 'audio'],
     outputs=[gr.Textbox(label="Transcribed Text", lines=15), gr.JSON(label="Transcribed JSON")]
 )