![]() ![]() ![]() The typical Json output from whisper-timestamped works, too. It exports one function: whisper_to_textgrid() Which takes in a transcription object (nested dict) from whisper-timestamped and returns a Textgrid object from praatio. ![]() To see what languages are available, please see the tokenizer.py file in the Whisper source (Yes, the OpenAI team themselves recommends finding it this way, too.) Using as a library m transcribe_allign_textgrid -model -language m transcribe_allign_textgrid -language In this case, you should install a light version of torch before installing whisper-timestamped (and thus this application). If you don't have a Nvidea GPU, or don't want to use it, you cannot use the CUDA platform on which Whisper is run.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |