Update app.py

app.py

@@ -31,11 +31,14 @@ def chunks_to_srt(chunks):
         srt_format += f"{i}\n{start_time_hms} --> {end_time_hms}\n{chunk['text']}\n\n"
     return srt_format
 
-def transcribe(inputs, task, return_timestamps):
+def transcribe(inputs, task, language, return_timestamps):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
-
-    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=return_timestamps)
+    
+    # Map the language names to their corresponding codes
+    language_codes = {"English": "en", "Korean": "ko", "Japanese": "ja"}
+    language_code = language_codes.get(language, "en")  # Default to "en" if the language is not found
+    result = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task, "language": f"<|{language_code}|>"}, return_timestamps=return_timestamps)
     
     if return_timestamps:
         return chunks_to_srt(result['chunks'])
@@ -135,6 +138,7 @@ file_transcribe = gr.Interface(
         gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
         gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
         gr.inputs.Checkbox(label="Return timestamps"),
+        gr.inputs.Dropdown(choices=["English", "Korean", "Japanese"], label="Language"),
     ],
     outputs="text",
     layout="horizontal",
@@ -154,6 +158,7 @@ yt_transcribe = gr.Interface(
         gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
         gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
         gr.inputs.Checkbox(label="Return timestamps"),
+        gr.inputs.Dropdown(choices=["English", "Korean", "Japanese"], label="Language"),
     ],
     outputs=["html", "text"],
     layout="horizontal",