hobodrifterdavid

@guillaumekln Oh, I have been watching the ctranslate2 and faster-whisper commits for this update, but missed these messages. Great. I'll give it a try in the next few days.

Okay, I got a bit of time free, and a machine to play on. @guillaumekln I followed the special build instructions, looks okay. So, what is needed is something like...

The speech-to-speech translation of this model is pretty good, there's an online demo here: https://seamless.metademolab.com/

In the paper they compare it to a cascaded approach (ASR, then translation, then TTS), I didn't look in detail, the nice thing here is it's all one model, easy...

btw, did you manage to convert a smaller Llama2 model ok with the convert CT2 script? EDIT: found the discussion in a closed issue: https://github.com/OpenNMT/CTranslate2/issues/1351

I made a script to load test script. Translating flores dataset EN => ES. Flores sentences are pretty long, newspaper-type sentence. Here the server handles a request, translate_batch is being...

Hmm. Ok, so seems I had an 'async' fastAPI handler, but then I was calling blocking functions inside it (translate_batch). If you don't have an 'async' request handler, fastAPI spawns...

@vince62s Hi Vince. One advantage of the sketch I made (there's no error handling etc. yet) is that one python process handles multiple concurrent requests. This means you can make...

Thanks Guillaume. ~~It was recommended to me to use split-sentences.perl logic from Moses. Sacremoses (a python reimplementation of some Moses scripts) doesn't have a complete reimplementation of split-sentences.perl, so I...

There was a nasty bug when batches were processed with multiple languages.. pushed a fix.. code seems pretty stable otherwise.