-
On translating a fine-tuned model from Huggingface Whisper to `ctranslate2` and running with faster whisper, i get extremely gibberish output.
I've tried it with various different versions but the…
-
Operaring system: Ubuntu 22.04.2, Python 3.10.6, CTranslate2 3.16.
When exporting the bigscience/bloomz model using:
_ct2-transformers-converter --force --model bigscience/bloomz --output_dir …
-
cuda version11.8
File "/App/install/OPS/pyenv/ai-speech/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1112, in forward
model_outputs = self._forward(model_inputs, **forwa…
-
https://zenn.dev/rinna/articles/5fd4f3cc12f7c5
-
The latest release of CTranslate2 python library from 10-22-2024 breaks faster-whisper. See release history here: https://pypi.org/project/ctranslate2/4.4.0/#history
I have created a pull request t…
-
Hello, how are you?
I am building faster-whisper windows POC by ctranslate2.
And i created ctranslate2::models::Whisper object whisperpool.
and write the code such as:
std::vector results;
result…
-
My script located here has a basic test now...
[https://github.com/collabora/WhisperSpeech/issues/67](https://github.com/collabora/WhisperSpeech/issues/67)
I'm excited about the concept of rever…
-
BLEU calculation occurs only on the CPU, perhaps this is somehow related to the function below
[eval.py#L56C44-L56C44](https://github.com/LibreTranslate/Locomotive/blob/975ef8a73c234d20e1938c806a4…
-
There is an obvious incorrect result when I translate Chinese to English,
input is '否', it means not or no, but I get yes, alternatives is wrong too, likes the image below
 and the ```bitsandbytes``` library at 4 and 8 bit...nicely done ctranslate2 people. Looking forward to testing GGUF in there as well.
![image](https:/…