-
|
Greetings! Help add a new model, please. ct2-transformers-converter --model mitchelldehaven/whisper-large-v2-ru --output_dir whisper-large-v2-ru-ct2 --copy_files tokenizer.json --quantization float16 I was advised to convert it, I seem to have succeeded with the help of these commands, but I don’t know how to add it. Support information please! |
Beta Was this translation helpful? Give feedback.
Replies: 6 comments 5 replies
-
|
Have model in |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
|
the model that I want to put is for the usual whisper, I managed to convert it with the command that I indicated above, but I don’t understand how to proceed. I was advised to use this command, but I do not understand how to use it. model = WhisperModel("/path/to/converted/model") " |
Beta Was this translation helpful? Give feedback.
-
|
Show what you get with |
Beta Was this translation helpful? Give feedback.
-
|
Model there is named |
Beta Was this translation helpful? Give feedback.
-
Here is where the problem lies. I was advised in the whisper-faster thread to do this. I did, but I can’t do the download, I don’t understand where to insert the second code. См. раздел «Преобразование модели» в README, чтобы преобразовать модель для более быстрого шепота: https://github.com/guillaumekln/faster-whisper#model-conversion . После преобразования модели вы можете загрузить ее из пути на диске: model = WhisperModel("/path/to/converted/model") |
Beta Was this translation helpful? Give feedback.






Have model in
_models\faster-whisper-large-v2-rufolder and use--model=large-v2-ru