ShmuelRonen / hebrew_whisper

Hebrew whisper powerful transcription and translation tool
MIT License
50 stars 6 forks source link

לא עובד. #7

Closed UberStorm closed 4 months ago

UberStorm commented 5 months ago

היי, מריץ שלל גרסאות של וויספר על המחשב אבל לא משנה מה הGIT הזה לא עובד לי. בכל פעם שאני לוחץ על sumbit אני מקבל את ההודעה הבאה ולאחר מכן כלום לא קורה, גם לאחר שעות: To create a public link, set share=True in launch(). Due to a bug fix in https://github.com/huggingface/transformers/pull/28687 transcription using a multilingual Whisper will default to language detection followed by transcription instead of translation to English.This might be a breaking change for your use case. If you want to instead always translate your audio to English, make sure to pass language='en'. E:\hebrew_whisper\venv\lib\site-packages\transformers\models\whisper\modeling_whisper.py:694: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.) attn_output = torch.nn.functional.scaled_dot_product_attention(

משתמש במחשב עם כרטיס מסך RTX 4070 Ti.

ShmuelRonen commented 5 months ago

אינני מצליח לשחזר את הבעיה אצלי. כמו כן הריפו עובד אצל הרבה אנשים ללא בעיה. האם נוצר venv בתוך הפולדר?

ShmuelRonen commented 5 months ago

שאלה נוספת. האם השורות האלו מופיעות אצלך:

Requirements installed. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:03<00:00, 1.52s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().

UberStorm commented 5 months ago

שאלה נוספת. האם השורות האלו מופיעות אצלך:

Requirements installed. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:03<00:00, 1.52s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().

היי, התשובה לשתי השאלות היא כן. הרצתי גם דרך קובץ הBAT וגם ידנית ואין הבדל. ניסיתי גם להוריד את זה מספר פעמים לכוננים שונים ותיקיות שונות, לא עזר.

ShmuelRonen commented 5 months ago

ומה קורה כשאתה פותח דף בדפדפן עם זה:http://127.0.0.1:7860/

UberStorm commented 5 months ago

ומה קורה כשאתה פותח דף בדפדפן עם זה:http://127.0.0.1:7860/

אולי לא הסברתי כמו שצריך, אבל הGUI כן עולה לי. לאחר שאני מכניס אודיו ולוחץ על SUMBIT, אני מקבל את ההודעה שהעתקתי והGUI טוען שעות מבלי שמתקבלת תוצאת תמלול/תרגום. כלומר, הוויספר לא רץ בפועל לאחר לחיצה על SUMBIT אצלי... image

UberStorm commented 5 months ago

(venv) E:\RVC\hebrew_whisper>python app.py Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:02<00:00, 1.17s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)> Traceback (most recent call last): File "C:\Users\maorg\AppData\Local\Programs\Python\Python310\lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "C:\Users\maorg\AppData\Local\Programs\Python\Python310\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host ERROR: Exception in ASGI application Traceback (most recent call last): File "E:\RVC\hebrew_whisper\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 407, in run_asgi result = await app( # type: ignore[func-returns-value] File "E:\RVC\hebrew_whisper\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 69, in call return await self.app(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\fastapi\applications.py", line 1054, in call await super().call(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\applications.py", line 123, in call await self.middleware_stack(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\middleware\errors.py", line 186, in call raise exc File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\middleware\errors.py", line 164, in call await self.app(scope, receive, _send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\middleware\cors.py", line 85, in call await self.app(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\middleware\exceptions.py", line 65, in call await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app raise exc File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\routing.py", line 756, in call await self.middleware_stack(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\routing.py", line 776, in app await route.handle(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\routing.py", line 297, in handle await self.app(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\routing.py", line 77, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 64, in wrapped_app raise exc File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\routing.py", line 75, in app await response(scope, receive, send) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\responses.py", line 352, in call await send( File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 50, in sender await send(message) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette_exception_handler.py", line 50, in sender await send(message) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\starlette\middleware\errors.py", line 161, in _send await send(message) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 504, in send output = self.conn.send(event=h11.Data(data=data)) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\h11_connection.py", line 469, in send data_list = self.send_with_data_passthrough(event) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\h11_connection.py", line 502, in send_with_data_passthrough writer(event, data_list.append) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\h11_writers.py", line 77, in call self.send_data(event.data, write) File "E:\RVC\hebrew_whisper\venv\lib\site-packages\h11_writers.py", line 97, in send_data raise LocalProtocolError("Too much data for declared Content-Length") h11._util.LocalProtocolError: Too much data for declared Content-Length Due to a bug fix in https://github.com/huggingface/transformers/pull/28687 transcription using a multilingual Whisper will default to language detection followed by transcription instead of translation to English.This might be a breaking change for your use case. If you want to instead always translate your audio to English, make sure to pass language='en'. E:\RVC\hebrew_whisper\venv\lib\site-packages\transformers\models\whisper\modeling_whisper.py:694: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.) attn_output = torch.nn.functional.scaled_dot_product_attention(

ShmuelRonen commented 5 months ago

מצב זה קורה בכל קובץ אודיו?

UberStorm commented 5 months ago

חוץ מהחלק האחרון שאני אצטט בעוד רגע, בקבצי אודיו מסוימים לא מופיעות שלל השגיאות שיש למעלה. אולי קשור לקידוד האודיו. אבל עדיין לא עובד גם כשאין את השגיאות האלה.

Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Due to a bug fix in https://github.com/huggingface/transformers/pull/28687 transcription using a multilingual Whisper will default to language detection followed by transcription instead of translation to English.This might be a breaking change for your use case. If you want to instead always translate your audio to English, make sure to pass language='en'. E:\RVC\hebrew_whisper\venv\lib\site-packages\transformers\models\whisper\modeling_whisper.py:694: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.) attn_output = torch.nn.functional.scaled_dot_product_attention(

ShmuelRonen commented 5 months ago

האם אף קובץ אודיו לא יוצר transcribe או translate?

UberStorm commented 5 months ago

כן, זה לא עובד עם אף קובץ. ניסיתי כמה בקידודים שונים. ניסיתי להחליף את גרסת הTORCH לגרסת 2.1.2 + cuda 11.8 והשגיאה האחרונה נעלמה, אבל התמלול/תרגום עצמם עדיין לא עובדים וזה טוען "לנצח".

Requirements installed. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:19<00:00, 9.90s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Due to a bug fix in https://github.com/huggingface/transformers/pull/28687 transcription using a multilingual Whisper will default to language detection followed by transcription instead of translation to English.This might be a breaking change for your use case. If you want to instead always translate your audio to English, make sure to pass language='en'. image

ShmuelRonen commented 5 months ago

כפי שכתבתי בהתחלה אינני יכול לשחזר את הבעיה אצלי. אולי תתקין את הריפוזיטורי עם סביבה וויטואלית של Anaconda

UberStorm commented 5 months ago

לא עובד לי גם דרך אנקונדה. באילו גרסאות פייתון וטורץ' אתה משתמש בסביבה שלך?

ShmuelRonen commented 5 months ago

(venv) E:\hebrew wispher>python Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] on win32 Type "help", "copyright", "credits" or "license" for more information.

(venv) E:\hebrew wispher>pip show torch Name: torch Version: 2.2.2+cu118 Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration Home-page: https://pytorch.org/ Author: PyTorch Team Author-email: packages@pytorch.org License: BSD-3 Location: e:\hebrew wispher\venv\lib\site-packages Requires: filelock, fsspec, jinja2, networkx, sympy, typing-extensions Required-by: openai-whisper, torchaudio, torchvision

(venv) E:\hebrew wispher>