logseq-whisper-subtitles-server's People
logseq-whisper-subtitles-server's Issues
Unable to create file locally from YouTube
First, thank you for providing such a great plugin. I try and do not know how to use. It looks like the file isn't downloading.
What I did; Run from the menu of the block with "{{youtube URL}}".
Error message:
logseq-whisper-subtitle-server error: [Errno 2] No such file or directory:
'D:\\ ------ \\logseq-whisper-subtitles-server\\logseq_whisper_subtitles_server\\.\\youtube/youtube_audio_6968954bf60841b48f987933359b93d3.mp3'
My guess is, the server is running. But the file was not found in the directory.
The system cannot find the file specified
Awesome concept. Really excited about it.
Installation of the server went without an issue.
Running python services.py results in The system cannot find the file specified error as discussed in the previous issue. I checked the whole thread to find out how the issue was resolved but failed to find a definitive answer. that's why opening new issue.
(logseq-transcription) C:\Users\Hp Pavilion\Documents\MERNStack\third-party-repos\logseq-whisper-subtitles-server\logseq_whisper_subtitles_server>python services.py
Loading base whisper model...
Loading base whisper model done.
=== English audio test
Using model: base
Transcribing Chinese simplified audio ...
C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\site-packages\whisper\transcribe.py:114: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Traceback (most recent call last):
File "C:\Users\Hp Pavilion\Documents\MERNStack\third-party-repos\logseq-whisper-subtitles-server\logseq_whisper_subtitles_server\services.py", line 147, in <module>
res_en = transcribe_audio("audio_english.mp3")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\Documents\MERNStack\third-party-repos\logseq-whisper-subtitles-server\logseq_whisper_subtitles_server\services.py", line 84, in transcribe_audio
transcribe = model.transcribe(audio=audio_path, verbose=True, initial_prompt="对于普通话句子,以中文简体输出") # 避免繁体输出
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\site-packages\whisper\transcribe.py", line 121, in transcribe
mel = log_mel_spectrogram(audio, padding=N_SAMPLES)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\site-packages\whisper\audio.py", line 140, in log_mel_spectrogram
audio = load_audio(audio)
^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\site-packages\whisper\audio.py", line 59, in load_audio
out = run(cmd, capture_output=True, check=True).stdout
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\subprocess.py", line 548, in run
with Popen(*popenargs, **kwargs) as process:
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\subprocess.py", line 1026, in __init__
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\Hp Pavilion\.conda\envs\logseq-transcription\Lib\subprocess.py", line 1538, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [WinError 2] The system cannot find the file specified
Not supported source yet for local video files
UnicodeEncodeError: 'charmap' codec can't encode character '\u4fdd' in position 26: character maps to <undefined>
I attempted to transcribe a Russian-language video that is over 40 minutes long.
I had one warning before:
C:\Python311\Lib\site-packages\whisper\transcribe.py:126: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Upon completion of the process, I received the following server error:
Traceback (most recent call last):
File "MyPath\logseq-whisper-subtitles-server\logseq_whisper_subtitles_server\app.py", line 74, in transcribe
"segments": transcribe_audio(audio_path, min_length, model_size, zh_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "MyPath\logseq-whisper-subtitles-server\logseq_whisper_subtitles_server\services.py", line 86, in transcribe_audio
transcribe = model.transcribe(audio=audio_path, verbose=True, initial_prompt="\u5bf9\u4e8e\u666e\u901a\u8bdd\u53e5\u5b50\uff0c\u4ee5\u4e2d\u6587\u7b80\u4f53\u8f93\u51fa") # \u907f\u514d\u7e41\u4f53\u8f93\u51fa
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\whisper\transcribe.py", line 466, in transcribe
print(make_safe(line))
File "C:\Python311\Lib\encodings\cp1251.py", line 19, in encode
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
UnicodeEncodeError: 'charmap' codec can't encode character '\u4fdd' in position 26: character maps to
127.0.0.1 - - [01/Mar/2024 13:10:34] "POST /transcribe HTTP/1.1" 200 -
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.