FormoSpeech

non-profit

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

txya900619 authored a paper about 2 months ago

A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech

txya900619 updated a model 3 months ago

formospeech/whisper-large-v2-formosan-all-ct2

txya900619 published a model 3 months ago

formospeech/whisper-large-v2-formosan-all-ct2

View all activity

spaces 1

Taiwanese Hakka Kaldi

Convert spoken Taiwanese Hakka into written Chinese text

models 15

formospeech/whisper-large-v2-formosan-all-ct2

Updated Jun 2 • 18

formospeech/whisper-large-v2-formosan-all

Automatic Speech Recognition • 2B • Updated May 16 • 12

formospeech/yourtts-htia-240704

Text-to-Speech • Updated Apr 7 • 98 • 1

formospeech/f5-tts-hakka-finetune

Text-to-Speech • Updated Apr 7

formospeech/whisper-small-formosan-all

Automatic Speech Recognition • 0.2B • Updated Apr 7 • 9 • 1

formospeech/whisper-large-v3-formosan-iso-prompt

Automatic Speech Recognition • 2B • Updated Apr 7 • 9

formospeech/whisper-large-v3-taiwanese-hakka

Automatic Speech Recognition • 2B • Updated Apr 7 • 464 • 6

formospeech/taiwanese-hakka-tts-sixian-hailu-mix-se

Text-to-Speech • Updated Jan 2 • 6 • 1

formospeech/kaldi-taiwanese-hakka-dapu

formospeech/kaldi-taiwanese-hakka-hailu

datasets 4

formospeech/AudioSCAN-XTTSv2-female

Updated Dec 19, 2024 • 6 • 1

formospeech/AudioSCAN-XTTSv2-male

Updated Dec 19, 2024 • 5

formospeech/AudioSCAN-StyleTTS2-female

Updated Dec 19, 2024 • 12

formospeech/AudioSCAN-StyleTTS2-male

Updated Dec 19, 2024 • 16