Hugging Face's logo

machinekind
/
Matcha-TTS-PL-Pretrain

Text-to-Speech
ONNX
Polish
matcha-tts
tts
polish
flow-matching
hifigan
multi-speaker
style-tokens
robot
pretraining
Model card Files
xet
 Community
Matcha-TTS-PL-Pretrain / samples

Commit History

25 days ago

  1. Default synthetic voice = Masiak 1, Staszczyk 0.5, Proszek 0.5 (UTMOS 3.38); female preset with three base-model women at 0.5

    mcPear
    Verified signature
    1863d68

26 days ago

  1. New default synthetic voice: Bielenia 0.7, Faszczewska 0.2, Masiak 1, Glogowski 0.15, Staszczyk 0.15 (UTMOS 3.49)

    mcPear
    Verified signature
    7403aa3

27 days ago

  1. default voice: synthetic (weighted blend of five readers); 7-reader preset removed

    mcPear
    Verified signature
    934d64f

28 days ago

  1. default voice: 7 readers equal share (Kopa 0), rescaled blending, temperature 0 recommended

    mcPear
    Verified signature
    4153160

  2. default voice: equal blend of all 8 readers (only preset); card and samples updated

    mcPear
    Verified signature
    ffc5410

  3. ONNX with spk_emb input (any blend/style at run time); voices.json = embedding tables + trio preset; Kopa blends removed

    mcPear
    Verified signature
    29857f3

  4. v3: Polish Matcha-TTS + fine-tuned HiFi-GAN vocoder, ONNX with baked voices

    mcPear
    Verified signature
    c24c082