Rino

i downgrade to 1.2.31 and sqlparse also 0.2.4 but still not works in docker

i've strange issue, i use sqlparse 0.2.4 and djongo 1.2.33 in local it run without trouble, but since i deploy it via docker to the server, its not work. its...

i imagine that every user have their own models to train based on the users need

also if i finetuned with singaporean english accent dataset, and not differentiate name of the speaker(put all voice training data in one folder and train it) will it still understand...

the training default configuration in parler-tts is max 30sec, max text length 600 https://github.com/huggingface/parler-tts/blob/main/training/README.md#3-training either you fine tune it with longer data, or send it in split if you're text...

you should create 1 middleware that can integrate between chat input -> ollama reply -> send to tortoise through socket_server, there is an example socket_client on how to consume it...

ok so the bare minimum to fitune is 11 hours I assume ? also my dataset format is in .lab like this inside `` 0.00 0.50 hello \n 0.51 1.00...

@PoTaTo-Mika what do you mean by compile the model ? also how to do quantized version? since I only do steps for inference in english documentation https://speech.fish.audio/en/inference/#2-create-a-directory-structure-similar-to-the-following-within-the-ref_data-folder

> there's a python file called quantize.py, you can view the file and choose to quantize.  its creating me a folder quantized version of the model now, just run...

in windows, if you already run this tortoise, it will creating cache for autoregressive.pth, that's the model exact location around C:\Users\-user-name-\.cache\tortoise\models\models--Manmay--tortoise-tts\snapshots\somestrings\autoregressive.pth , if you found urdu language model just rename...