Updated character prompt

Merge branch 'refactor' into hf

Refactor CLI to support multiple query audio inputs

increase max_sentences from 2 to 5 for improved response generation.

Add more iterations to prompt gemini

update character prompt for better performance in current models

change bilingual svs to use espnet/mixdata_svs_visinger2_spkemb_lang_pretrained_avg

Merge pull request #3 from Masao-Someki/feature/add_per

Move initialization process to init_per()

Merge branch 'refactor' into feature/add_per

update eval prototypes for per

Update PER calculation

Merge branch 'refactor' of github.com:Masao-Someki/SingingSDS-dev into feature/add_per

Add asr model for PER

update PER placeholder

Revert "add per template"

add per template

specify basic-pitch version to 0.4.0 in requirements.txt

remove tensorflow from requirements.txt

Merge branch 'refactor' into hf

fix basic pitch env

fix yaoyin image path

Merge remote-tracking branch 'hf/main' into hf

Update Yaoyin character image format from JPG to PNG

Update requirements.txt

Merge branch 'refactor' into hf

Add tensorflow dependency to requirements.txt

Revert "Add tensorflow dependency to requirements.txt"

Add tensorflow dependency to requirements.txt

Merge branch 'refactor' into hf

Merge remote-tracking branch 'origin/refactor' into refactor

Add SingMOS and s3prl dependencies to requirements.txt

Merge branch 'refactor' into hf

update requirements.txt

hugging face specific changes

Update requirements.txt to include new dependencies for Gemini and FunASR

Remove unnecessary metadata from README.md

Merge remote-tracking branch 'hf/main' into hf

Merge branch 'refactor' into hf

Update Yaoyin's character image

espnet mixed svs bug fixed

updated config

fix espnet mixed svs

Include model cleanup

Update prompt for better performance using newly added llms

Add get_character function

fix aesthetic eval

add more llms; add system prompt support; add device=auto

Add MiniMax-Text-01 support

add reference link