Update app.py

app.py

@@ -370,8 +370,54 @@ with gr.Blocks() as interface:
     """
     )
     with gr.Tabs():
-        with gr.TabItem("LLMs"):
-            with gr.Row():
+        with gr.Tabs():
+            with gr.TabItem("Transcription"):
+                gr.Markdown("Transcript audio from files to text!")
+                with gr.Row():
+                    audio_input = gr.File(type="filepath", label="Upload File containing Audio", file_types=[f".{ext}" for ext in ALLOWED_FILE_EXTENSIONS])
+                    model_choice_transcribe = gr.Dropdown(choices=["whisper-large-v3"],value="whisper-large-v3",label="Model")                                                    
+                with gr.Row():
+                    transcribe_prompt = gr.Textbox(label="Prompt (Optional)",info="Specify any context or spelling corrections.")
+                    with gr.Column():
+                        language = gr.Dropdown(
+                            choices=[(lang, code) for lang, code in LANGUAGE_CODES.items()],
+                            value="en",
+                            label="Language",
+                        )
+                        
+                        auto_detect_language = gr.Checkbox(label="Auto Detect Language")
+                    transcribe_button = gr.Button("Transcribe")
+                    transcription_output = gr.Textbox(label="Transcription")
+                    merged_audio_output = gr.File(label="Merged Audio (if chunked)")
+                    transcribe_button.click(
+                        transcribe_audio,
+                        inputs=[audio_input, model_choice_transcribe, transcribe_prompt, language, auto_detect_language],
+                        outputs=[transcription_output, merged_audio_output],
+                    )
+            with gr.TabItem("Translation"):
+                gr.Markdown("Transcript audio from files and translate them to English text!")
+                with gr.Row():
+                    audio_input_translate = gr.File(
+                        type="filepath", label="Upload File containing Audio", file_types=[f".{ext}" for ext in ALLOWED_FILE_EXTENSIONS]
+                    )
+                    model_choice_translate = gr.Dropdown(
+                        choices=["whisper-large-v3"],
+                        value="whisper-large-v3",
+                        label="Audio Speech Recognition (ASR) Model",
+                    )
+                with gr.Row():
+                    translate_prompt = gr.Textbox(
+                        label="Prompt (Optional)",
+                        info="Specify any context or spelling corrections.",
+                    )
+                    translate_button = gr.Button("Translate")
+                    translation_output = gr.Textbox(label="Translation")
+                    translate_button.click(
+                        translate_audio,
+                        inputs=[audio_input_translate, model_choice_translate, translate_prompt],
+                        outputs=translation_output,
+                    )
+            with gr.TabItem("LLMs"):
                 with gr.Column(scale=1, min_width=250):
                     model = gr.Dropdown(
                         choices=[
@@ -425,62 +471,6 @@ with gr.Blocks() as interface:
                         ],
                     )
                     model.change(update_max_tokens, inputs=[model], outputs=max_tokens)
-        with gr.TabItem("Speech To Text"):
-            with gr.Tabs():
-                with gr.TabItem("Transcription"):
-                    gr.Markdown("Transcript audio from files to text!")
-                    with gr.Row():
-                        audio_input = gr.File(
-                            type="filepath", label="Upload File containing Audio", file_types=[f".{ext}" for ext in ALLOWED_FILE_EXTENSIONS]
-                        )
-                        model_choice_transcribe = gr.Dropdown(
-                            choices=["whisper-large-v3"],
-                            value="whisper-large-v3",
-                            label="Model",
-                        )
-                    with gr.Row():
-                        transcribe_prompt = gr.Textbox(
-                            label="Prompt (Optional)",
-                            info="Specify any context or spelling corrections.",
-                        )
-                    with gr.Column():
-                        language = gr.Dropdown(
-                            choices=[(lang, code) for lang, code in LANGUAGE_CODES.items()],
-                            value="en",
-                            label="Language",
-                        )
-                        auto_detect_language = gr.Checkbox(label="Auto Detect Language")
-                    transcribe_button = gr.Button("Transcribe")
-                    transcription_output = gr.Textbox(label="Transcription")
-                    merged_audio_output = gr.File(label="Merged Audio (if chunked)")
-                    transcribe_button.click(
-                        transcribe_audio,
-                        inputs=[audio_input, model_choice_transcribe, transcribe_prompt, language, auto_detect_language],
-                        outputs=[transcription_output, merged_audio_output],
-                    )
-                with gr.TabItem("Translation"):
-                    gr.Markdown("Transcript audio from files and translate them to English text!")
-                    with gr.Row():
-                        audio_input_translate = gr.File(
-                            type="filepath", label="Upload File containing Audio", file_types=[f".{ext}" for ext in ALLOWED_FILE_EXTENSIONS]
-                        )
-                        model_choice_translate = gr.Dropdown(
-                            choices=["whisper-large-v3"],
-                            value="whisper-large-v3",
-                            label="Audio Speech Recognition (ASR) Model",
-                        )
-                    with gr.Row():
-                        translate_prompt = gr.Textbox(
-                            label="Prompt (Optional)",
-                            info="Specify any context or spelling corrections.",
-                        )
-                    translate_button = gr.Button("Translate")
-                    translation_output = gr.Textbox(label="Translation")
-                    translate_button.click(
-                        translate_audio,
-                        inputs=[audio_input_translate, model_choice_translate, translate_prompt],
-                        outputs=translation_output,
-                    )
                     
                     
 interface.launch(share=True)