fixed

app.py

@@ -42,7 +42,7 @@ def transcribe(inputs, task, return_timestamps, language):
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
     # Map the language names to their corresponding codes
-    language_codes = {"English": "en", "Uzbek": "uzbek"}
+    language_codes = {"English": "en", "Uzbek": "uz"}
     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)
@@ -107,7 +107,7 @@ def yt_transcribe(yt_url, task, return_timestamps, language, max_filesize=75.0):
     inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
 
     # Map the language names to their corresponding codes
-    language_codes = {"English": "en", "Uzbek": 'uzbek'}
+    language_codes = {"English": "en", "Uzbek": "uz"}
     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}|>"},
@@ -121,32 +121,32 @@ def yt_transcribe(yt_url, task, return_timestamps, language, max_filesize=75.0):
 
 demo = gr.Blocks()
 
-# mf_transcribe = gr.Interface(
-#     fn=transcribe,
-#     inputs=[
-#         gr.Audio(sources=["microphone"], type="filepath"),
-#         gr.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-#         gr.Checkbox(label="Return timestamps"),
-#         gr.Dropdown(choices=["English", "Uzbek"], label="Language"),
-#     ],
-#     outputs="text",
-#     layout="horizontal",
-#     theme="huggingface",
-#     title="Whisper Large V3 Uzbek: Transcribe Audio",
-#     description=(
-#         "\n\n"
-#         "<center>⭐️Brought to you by <a href='https://note.com/sangmin/n/n9813f2064a6a'>Chiomirai School</a>⭐️</center>"
-#     ),
-#     allow_flagging="never",
-# )
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+        gr.inputs.Checkbox(label="Return timestamps"),
+        gr.inputs.Dropdown(choices=["English", "Uzbek"], label="Language"),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Large V3 Uzbek: Transcribe Audio",
+    description=(
+        "\n\n"
+        "<center>⭐️Brought to you by <a href='https://note.com/sangmin/n/n9813f2064a6a'>Chiomirai School</a>⭐️</center>"
+    ),
+    allow_flagging="never",
+)
 
 file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.Audio(sources=["upload"], type="filepath", label="Audio file"),
-        gr.Radio(["transcribe", "translate"], label="Task"),
-        gr.Checkbox(label="Return timestamps"),
-        gr.Dropdown(choices=["English", "Uzbek"], label="Language"),
+        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", "Uzbek"], label="Language"),
     ],
     outputs="text",
     layout="horizontal",
@@ -159,24 +159,24 @@ file_transcribe = gr.Interface(
     allow_flagging="never",
 )
 
-# yt_transcribe = gr.Interface(
-#     fn=yt_transcribe,
-#     inputs=[
-#         gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
-#         gr.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
-#         gr.Checkbox(label="Return timestamps"),
-#         gr.Dropdown(choices=["English", "Uzbek"], label="Language"),
-#     ],
-#     outputs=["html", "text"],
-#     layout="horizontal",
-#     theme="huggingface",
-#     title="Whisper Large V3 Uzbek: Transcribe YouTube",
-#     description=(
-#         "\n\n"
-#         "<center>⭐️Brought to you by <a href='https://note.com/sangmin/n/n9813f2064a6a'>Chiomirai School</a>⭐️</center>"
-#     ),
-#     allow_flagging="never",
-# )
+yt_transcribe = gr.Interface(
+    fn=yt_transcribe,
+    inputs=[
+        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", "Uzbek"], label="Language"),
+    ],
+    outputs=["html", "text"],
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Large V3 Uzbek: Transcribe YouTube",
+    description=(
+        "\n\n"
+        "<center>⭐️Brought to you by <a href='https://note.com/sangmin/n/n9813f2064a6a'>Chiomirai School</a>⭐️</center>"
+    ),
+    allow_flagging="never",
+)
 
 with demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])

requirements.txt

@@ -1,4 +1,4 @@
 git+https://github.com/huggingface/transformers
 torch
 yt-dlp
-gradio
+gradio==3.36.1