lewangdev / autotranslate

Videos Transcription and Translation with Faster Whisper and ChatGPT

Hi there 👋

I'm Le, a software engineer.

• 📫 How to reach me: Twitter
• 📧 or send me a Email
• 🔥 My blog: lewang.dev

autotranslate's Issues

How to get model to run on all files when given Google Drive folder path?

I input the folder path of Google Drive, and it also printed out that 64 files were selected. But when I "Run the model", it only runs the last file. How can I adjust or modify this?

日文字幕translate之後還是日文

請問是否我哪邊設定有問題呢?

可以支持自定义api url吗

希望能够支持这个特性

提示错误

UnboundLocalError Traceback (most recent call last)
in <cell line: 101>()
99 return fragments_translated
100
--> 101 fragments_translated = translate_fragments(new_fragments, count_of_sentence_send_once_limit)
102
103 # Save translation as json file

1 frames
in translate_by_chatgpt(sentences, max_retry_times, deployment_id, model_name, temperature)
73 print(f"==Tranlate Retry with {current_retry_times} times")
74 continue
---> 75 return sentences_translated
76
77 def translate_fragments(fragments, sentence_send_limit=5):

UnboundLocalError: local variable 'sentences_translated' referenced before assignment

feature request : groq.com api key can implement

Hi lewangdev,
please support groq.com as supported api keys near azure & openai
waiting for your commit about it
regards

怎么解决Colab提示使用限额

才用了一天

Problems with broken sentences in the bilingual subtitles generated

Hi @lewangdev, thanks so much for your script. Sometimes I encounter problems with broken sentences in the bilingual subtitles generated during the process, resulting in some source language subtitles missing translated subtitles.
Have you ever encountered this situation?

Supplementing a bit, I am using a third-party API, not OpenAI API.

希望对日语优化~ 大家转录、翻译日语的时候是什么设置呢

如题 这个是普遍需求吧~

error

RuntimeError Traceback (most recent call last)
in <cell line: 45>()
43 fragments = []
44
---> 45 for segment in segments:
46 print(f"[{seconds_to_time_format(segment.start)} --> {seconds_to_time_format(segment.end)}] {segment.text}")
47 if word_level_timestamps:

1 frames
/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py in encode(self, features)
627 features = get_ctranslate2_storage(features)
628
--> 629 return self.model.encode(features, to_cpu=to_cpu)
630
631 def generate_with_fallback(

RuntimeError: Library libcublas.so.11 is not found or cannot be loaded

Feature update request

In addition, can the translation function of gpt4 be supported? Many new models have been added to the openai official website. Can they be added?

[BUG]There seems to be a problem with Import libraries for Python