Running
on
Zero
430
🥖
Parler-TTS Mini
High-fidelity Text-To-Speech
Open-source speech datasets annotated using Data-Speech
Open-source annotated speech datasets ranging from 1,000 hours to soon 50,000 hours.
-
blabble-io/libritts_r
Viewer • Updated • 3.86k • 7Note A 1K hours high-quality English speech dataset.
parler-tts/libritts_r_tags_tagged_10k_generated
Viewer • Updated • 2.19k • 3Note An annotated version of LibriTTS-R above.
parler-tts/mls_eng_10k
Viewer • Updated • 20k • 9Note A 10K hours subset of the English version of the Multilingual LibriSpeech (MLS) dataset.
parler-tts/mls-eng-10k-tags_tagged_10k_generated
Viewer • Updated • 871 • 9Note Annotations of the 10K hours subset of English MLS above.
parler-tts/parler_tts_mini_v0.1
Text-to-Speech • Updated • 42.7k • 290Note A first model iteration of Parler-TTS, trained using the 10k hours of narrated audiobooks above.
-
Natural language guidance of high-fidelity text-to-speech with synthetic annotations
Paper • 2402.01912 • Published • 7