-
StyleTTS2: Ukrainian text to speech
π147StyleTTS2 trained on Ukrainian multispeaker dataset
-
RAD-TTS++ Ukrainian (HiFiGAN)
π§4Use RAD-TTS++ model to synthesize text in Ukrainian
-
RAD-TTS++ Ukrainian (Vocos)
π§2Use RAD-TTS++ model to synthesize text in Ukrainian
-
RAD-TTS++ Ukrainian (BigVGAN v2)
π§1Use RAD-TTS++ model to synthesize text in Ukrainian
AI & ML interests
We are driving innovation in Ukrainian speech technology πΊπ¦
Recent Activity
View all activity
Organization Card
Hello or ΠΡΠΈΠ²ΡΡ [preΛuΜ―Κ²it] π
The Speech-UK initiative is dedicated to developing and providing speech technologies for the Ukrainian language, available globally.
Our activities include:
- Dataset creation and curation;
- Model training and development;
- Tool creation and open-source repository maintenance.
Community:
- Discord: https://bit.ly/discord-uds
- Speech Recognition: https://t.me/speech_recognition_uk
- Speech Synthesis: https://t.me/speech_synthesis_uk
π€ Support our work using Monobank or give us a Star on https://github.com/egorsmkv/speech-recognition-uk
-
Speech-to-Text for Ukrainian v2.1 (W2V-BERT 2.0)
π2Transcribe Ukrainian audio files to text
-
Yehor/w2v-bert-uk-v2.1
Automatic Speech Recognition β’ 0.6B β’ Updated β’ 201 β’ 3 -
Yehor/whisper-large-v3-turbo-quantized-uk
0.2B β’ Updated β’ 135 β’ 2 -
Yehor/whisper-large-v2-quantized-uk
0.3B β’ Updated β’ 37
-
StyleTTS2: Ukrainian text to speech
π147StyleTTS2 trained on Ukrainian multispeaker dataset
-
RAD-TTS++ Ukrainian (HiFiGAN)
π§4Use RAD-TTS++ model to synthesize text in Ukrainian
-
RAD-TTS++ Ukrainian (Vocos)
π§2Use RAD-TTS++ model to synthesize text in Ukrainian
-
RAD-TTS++ Ukrainian (BigVGAN v2)
π§1Use RAD-TTS++ model to synthesize text in Ukrainian
-
Speech-to-Text for Ukrainian v2.1 (W2V-BERT 2.0)
π2Transcribe Ukrainian audio files to text
-
Yehor/w2v-bert-uk-v2.1
Automatic Speech Recognition β’ 0.6B β’ Updated β’ 201 β’ 3 -
Yehor/whisper-large-v3-turbo-quantized-uk
0.2B β’ Updated β’ 135 β’ 2 -
Yehor/whisper-large-v2-quantized-uk
0.3B β’ Updated β’ 37
spaces 10
pinned
No application file
1
Ukrainian Text-to-Speech Leaderboard
π
pinned
No application file
1
Ukrainian Speech-to-Text Leaderboard
π
pinned
Sleeping
MaskLID
π¨
Identify languages in code-switched text
Running
7
VAD with MarbleNet
π£
Voice Activity Detection using MarbleNet model
Running
KenLM UI
π
Build KenLM models via UI and score texts
datasets 27
speech-uk/radio-free-europe
Updated
speech-uk/yodas2
Viewer β’ Updated β’ 400k β’ 151 β’ 1
speech-uk/openstt
Updated β’ 9
speech-uk/cv22
Viewer β’ Updated β’ 89.2k β’ 21
speech-uk/broadcast
Viewer β’ Updated β’ 137k β’ 214 β’ 2
speech-uk/voa
Viewer β’ Updated β’ 326k β’ 126 β’ 1
speech-uk/cv10-uk-testset-clean-zipa
Viewer β’ Updated β’ 3.2k β’ 9
speech-uk/cs-sentences
Updated β’ 4
speech-uk/surzhyk-sentences
Updated β’ 7
speech-uk/voa-test-compare-sidon
Viewer β’ Updated β’ 3.93k β’ 47