Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
machinekind
/
Matcha-TTS-PL
Like
5
Follow
Machinekind
16
Text-to-Speech
ONNX
Polish
matcha-tts
tts
polish
flow-matching
hifigan
distillation
voxcpm2
code-switching
robot
multi-voice
License:
cc-by-sa-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
Matcha-TTS-PL
/
samples
/
female_voxcpm_2
4.79 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
mcPear
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
9988b7b
verified
about 1 month ago
README.md
Safe
2.03 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e01.wav
Safe
95.8 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e01_teacher.wav
111 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e02.wav
Safe
92.2 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e02_teacher.wav
108 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e03.wav
Safe
74.8 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e03_teacher.wav
Safe
77.7 kB
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e04.wav
Safe
71.7 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e04_teacher.wav
Safe
78.1 kB
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e05.wav
Safe
176 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e05_teacher.wav
186 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e06.wav
177 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e06_teacher.wav
Safe
192 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e07.wav
Safe
234 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e07_teacher.wav
251 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e08.wav
Safe
16.4 kB
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e08_teacher.wav
Safe
22.2 kB
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e09.wav
131 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e09_teacher.wav
Safe
144 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e10.wav
423 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e10_teacher.wav
461 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e11.wav
553 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e11_teacher.wav
588 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago
e12.wav
253 kB
xet
Defaults for every voice: temperature 0.8, tempo 0.8 (voices_index, voices.json, card); samples of the new voices regenerated at these defaults
about 1 month ago
e12_teacher.wav
271 kB
xet
Three more synthetic voices (female_voxcpm_1, male_voxcpm_2, female_voxcpm_2): one Matcha model + own HiFi-GAN each, onnx/<voice>/, voices_index.json; card and attribution for four voices
about 1 month ago