![]() ![]() ![]() Python audiototext.py examples/multi-language/english_japanese.mp3 -output_formats txt,vtt,srt -api_key sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx # Transcribe english_japanese.mp3 using API to TXT, VTT and SRT formats Python audiototext.py examples/french-to-english/french.wav -task translate -language French -output_format txt # Translate french.wav from French to English using small model to TXT format Python audiototext.py examples/english/english.wav -model large-v2 -output_dir audio_transcription # Transcribe english.wav using large-v2 model to TXT, VTT, SRT, TSV and JSON formats Clone this repository or download the audiototext.py script ( right-click -> Save as.).Using AudioToText CLIĪ plain python script is available to use in your system without Jupyter. You might, however, try to use the smaller models ( tiny, base, small) on your CPU. You can also use them locally without a powerful GPU using API, as it always runs in the cloud.ĬPU execution is also available, but it is much slower and the Colab version or API is recommended if you do not have a decent GPU. If you have a powerful computer with GPU hardware acceleration, you can run the notebook or CLI in your local machine. With audio-only files you will need to enable a visualization in Audio -> Visualizations. If you use VLC to play video or audio files, you can add your vtt or srt transcripts as captions by drag-and-drop the transcript file to the media player or go to Subtitles -> Add Subtitle File. Transcript files will be located in the audio_transcription folder. Vtt or srt are recommended to add captions to an audio or video. Txt is recommended to read a transcription. Output_formats: Select the desired transcript formats (comma-separated)Īvailable formats: txt, vtt, srt, tsv, json See this example with audio transcriptions in different languages using Whisper and translation to spanish using DeepL. If you exceed your free quota you can upgrade to DeepL API Pro or try using the Free Translator Files web feature uploading the generated transcripts. The DeepL API has a free quota of 500,000 characters per month. Language: Auto-Detect or select the source language of your audio file * Supported source languages by DeepL However, as an alternative you can use DeepL API to translate the transcription to another language. Translation to other languages than English is not supported by Whisper. Language: Auto-Detect or select the source language of your audio file Audio translation using DeepL translator Language: Auto-Detect or select the source language of your audio file Supported source languages by WhisperĪudio translation to English using Whisper Language: English Audio transcription from almost any language using Whisper There are several examples in the examples folder.Īudio transcription from English using Whisper ![]() Save transcriptions and captions in different formats: TXT, VTT, SRT, TSV and JSON.Ĭhoose between open-source models or API. Translate the transcriptions using DeepL translator. If you want to run the code in your own computer check local installation. Open AudioToText in Google Colab and follow the step-by-step instructions.Ī Cloud GPU will be assigned to you to run the notebook code to transcribe and translate your audio files. □□ Vídeo sobre Whisper (Dot CSV) How to use Generate captions using VTT or SRT file formats. Translate audio using Whisper and DeepL translator. Transcribe audio using Whisper from OpenAI. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |