Update app.py

app.py

@@ -1,3 +1,8 @@
+import streamlit as st
+import pandas as pd
+import os
+import datetime
+import subprocess
 # import whisper
 from faster_whisper import WhisperModel
 import datetime
@@ -345,70 +350,33 @@ def speech_to_text(video_file_path, selected_source_lang, whisper_model, num_spe
         raise RuntimeError("Error Running inference with local model", e)
 
 
-# ---- Gradio Layout -----
-# Inspiration from https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles
-video_in = gr.Video(label="Video file", mirror_webcam=False)
-youtube_url_in = gr.Textbox(label="Youtube url", lines=1, interactive=True)
-df_init = pd.DataFrame(columns=['Start', 'End', 'Speaker', 'Text'])
-memory = psutil.virtual_memory()
-selected_source_lang = gr.Dropdown(choices=source_language_list, type="value", value="en", label="Spoken language in video", interactive=True)
-selected_whisper_model = gr.Dropdown(choices=whisper_models, type="value", value="base", label="Selected Whisper model", interactive=True)
-number_speakers = gr.Number(precision=0, value=0, label="Input number of speakers for better results. If value=0, model will automatic find the best number of speakers", interactive=True)
-system_info = gr.Markdown(f"*Memory: {memory.total / (1024 * 1024 * 1024):.2f}GB, used: {memory.percent}%, available: {memory.available / (1024 * 1024 * 1024):.2f}GB*")
-download_transcript = gr.File(label="Download transcript")
-transcription_df = gr.DataFrame(value=df_init,label="Transcription dataframe", row_count=(0, "dynamic"), max_rows = 10, wrap=True, overflow_row_behaviour='paginate')
-title = "Whisper speaker diarization"
-demo = gr.Blocks(title=title)
-demo.encrypt = False
-
-
-with demo:
-    with gr.Tab("Med Speech Pro"):
-        gr.Markdown('''
-            <div>
-            <h1 style='text-align: center'>Med Speech Pro : Lightning-Fast</h1>
-            Description: Experience Rapid Speech Recognition and Seamless Speaker identification With SpeechPro, a cutting-edge solution for accurate Medical Transcription
-            </div>
-        ''')
-        with gr.Row():
-            with gr.Column():
-                youtube_url_in.render()
-                download_youtube_btn = gr.Button("Download Youtube video")
-                download_youtube_btn.click(get_youtube, [youtube_url_in], [
-                    video_in])
-                print(video_in)
-                
-
-        with gr.Row():
-            with gr.Column():
-                video_in.render()
-                with gr.Column():
-                    gr.Markdown('''.
-                    ''')
-                selected_source_lang.render()
-                selected_whisper_model.render()
-                number_speakers.render()
-                transcribe_btn = gr.Button("Transcribe Now")
-                transcribe_btn.click(speech_to_text, 
-                                     [video_in, selected_source_lang, selected_whisper_model, number_speakers], 
-                                     [transcription_df, system_info, download_transcript]
-                                    )
-                
-        with gr.Row():
-            gr.Markdown('''
-            ##### Results
-            ##### ''')
-            
+# Streamlit app layout
+st.title('Med Speech Pro : Lightning-Fast')
+st.markdown('Experience Rapid Speech Recognition and Seamless Speaker identification With SpeechPro, a cutting-edge solution for accurate Medical Transcription')
 
-        with gr.Row():
-            with gr.Column():
-                download_transcript.render()
-                transcription_df.render()
-                system_info.render()
-                gr.Markdown('''<center><img src='https://visitor-badge.glitch.me/badge?page_id=WhisperDiarizationSpeakers' alt='visitor badge'><a href="https://opensource.org/licenses/Apache-2.0"><img src='https://img.shields.io/badge/License-Apache_2.0-blue.svg' alt='License: Apache 2.0'></center>''')
+# Handling YouTube URL input
+youtube_url = st.text_input("Enter YouTube URL")
 
-                
-    
-    
+if st.button('Download YouTube Video'):
+    # Call your function to handle YouTube video downloading
+    video_file_path = get_youtube(youtube_url)
+    st.video(video_file_path)
+
+# File Uploader for videos
+video_file = st.file_uploader("Upload a video file", type=["mp4", "avi", "mov"])
+
+selected_source_lang = st.selectbox("Select Spoken Language in Video", source_language_list)
+selected_whisper_model = st.selectbox("Select Whisper Model", whisper_models)
+number_of_speakers = st.number_input("Number of Speakers (0 for automatic detection)", min_value=0, value=0)
+
+if st.button('Transcribe Video'):
+    if video_file is not None:
+        # Process the video file
+        df_results, system_info, save_path = speech_to_text(video_file, selected_source_lang, selected_whisper_model, number_of_speakers)
+        st.dataframe(df_results)
+        st.markdown(system_info)
+        st.download_button('Download Transcript', data=pd.read_csv(save_path).to_csv(), file_name='transcript.csv')
+    else:
+        st.error("Please upload a video file or download one from YouTube.")
 
-demo.launch(debug=True,share=True)
+# Additional components and functionalities can be added here as needed.