NOW. We say hello to the future.

print the response

print the response

use JSON

Hello, future.

Use llama-cpp-python

Use hf_hub_download properly

Use quantized model

m3b

Inital MiniChat test

KEEP LICKING

AAAAH

Add description for transcription

Meow

Fixed transcription

Change interface id

We should probably use the correct stt function

Add whisper transcription

Reformat to actually fit API Doc standards

Added API route for synthesize

app.py: remove extra global declaration

app.py: add locker

add global keyword

reload model on synthesis if needed

Set concurrency_count=1

Add queue

Change /data to data

fix typo

huggingface_hub.Repository doesnt work

use /data as a model dir

fix the model location

add missing imports

Pre-download all the models

app.py: accompany for variable sampling rate of models

bump balacoon_tts version

app.py: list only CPU models from model repo

app.py: all models multispeaker, fix instructions

Update balacoon-tts version

app.py: small comment adjustment to rebuild the app

app.py: cut off, if the input is too long

Change variant to panel for Columns and Rows, otherwise not visible

Initial commit