Soshy's picture

13 19

Soshy

Respair

·

MystiqCaleid

AI & ML interests

Speech and Audio Processing, Natural Language Processing

Organizations

spaces 1

StyleTTS 2

Efficient, fast, and natural text to speech with StyleTTS 2!

models 7

Respair/Japanese_Phoneme_to_Grapheme_LLM

Text Generation • Updated 8 days ago • 31 • 1

Respair/Hibiki_ASR_Encoder

Updated 10 days ago

Respair/Qwen2_Audio_Encoder

Feature Extraction • Updated 10 days ago • 15

Respair/Hibiki_ASR_Phonemizer_v0.2

Updated 29 days ago • 135 • 2

Respair/emotion_2_vec_plus_older_but_better_ckpt

Respair/deberta-v3-large-finetuned-style

Respair/dal-bert-finetuned-emotion

Text Classification • Updated Apr 30 • 6

datasets 15

Respair/TD_Eng

Preview • Updated 8 days ago

Respair/Japanese_Phoneme_to_Grapheme_DS_PLUS

Viewer • Updated 15 days ago • 2M • 11 • 1

Respair/DL_3

Preview • Updated Aug 16 • 2 • 1

Respair/ehehe_chunk

Viewer • Updated Aug 15 • 4k • 2 • 1

Respair/Whisper_GL

Viewer • Updated Aug 11 • 23.2k • 2 • 1

Respair/JPl_Whisp_cv

Viewer • Updated Aug 10 • 28.9k • 2 • 1

Respair/sharegpt_chatml_compressed

Viewer • Updated Jul 18 • 94.1k • 2

Respair/Tokenized_Text-PH_Updated

Viewer • Updated Jul 16 • 525k • 2

Respair/t_test

Viewer • Updated Jun 8 • 10k • 2

Respair/Style_vectors_JPN

Viewer • Updated May 31 • 4.61k • 2