CTranslate2
CTranslate2 copied to clipboard
Fast inference engine for Transformer models
It would be awesome if your `generate_batch()` function could support an `end_sequence` parameter (stopping the generation as soon as a specific token is reached): https://huggingface.co/docs/transformers/v4.21.1/en/main_classes/text_generation#transformers.generation_utils.GenerationMixin In my opinion this parameter...
I tried to pip ctranslate2>=2.17.0 and I found out that there is no such package ``` # uname -a Linux blackpi 5.10.63-v7l+ #1496 SMP Wed Dec 1 15:58:56 GMT 2021...
Hello again, I'm trying to convert this adaptation of Bart Large MNLI: https://huggingface.co/joeddav/bart-large-mnli-yahoo-answers It returns the following error (but the base Bart Large MNLI model works well): ``` Traceback (most...
Hi, i have converted a fine-tuned opennmt model to ctranslate. The problem is I am getting different translation on same input on different machines. sample input sentence: `Sportsman Jhonathan Florez...
Hi! I would like to use `ct2-fairseq-converter` to translate an existing fairseq trained model. However, since the converter supports a limited set of architectures, wondering what the best approach to...
Hello, I know this is for a specific use-case but today the score_batch() function returns only the argmax() which enables only to score and get the logprob/perplexity of a sentence,...
Fairseq recently released a new version 0.12.1 to PyPI. This version is breaking the conversion of M2M-100 which fails with the following error: ```text Traceback (most recent call last): File...
Hi. I want to implement a feature to train a generic translation model on a large dataset, where we have many translator users, each of whom has a personal memory...
Are there any plans to support inference of heterogeneous encoder-decoder architectures where in we use transformer based encoder and RNN/LSTM based decoders ? Would like to submit this as a...