Update app.py

app.py

@@ -27,6 +27,7 @@ import contextlib
 from transformers import pipeline
 import psutil
 import openai
+import tempfile
 
 whisper_models = ["tiny", "base", "small", "medium", "large-v1", "large-v2"]
 source_languages = {
@@ -287,7 +288,7 @@ 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="ja",
+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)
@@ -307,6 +308,7 @@ openai_prompt_in = gr.TextArea(label="openai_prompt", value="""会議の文字
 - 会議の内容
 - 会議の結果""")
 openai_summary_out = gr.Textbox(label="openai_summary")
+save_path = "output/transcript_result.csv"
 
 title = "Whisper speaker diarization"
 demo = gr.Blocks(title=title)
@@ -385,7 +387,7 @@ with demo:
                 openai_prompt_in.render()
                 openai_summary_btn = gr.Button("Evaluate and analyze transcription content")
                 openai_summary_btn.click(create_transcription_summary,
-                                         [openai_key_in, openai_prompt_in, download_transcript],
+                                         [openai_key_in, openai_prompt_in, save_path],
                                          [openai_summary_out]
                                          )