This dataset contains text-and-audio pairs selected for TTS training. The initial audio/uzbek split has 2,184 utterances. Other languages and additional rows can be added as separate, append-only shards. Each row retains the complete structured text specification alongside audio and the OmniVoice fields utt, text, spk, and instruct. ttstaggedtext preserves the local delivery and vocal-event controls separately from the clean text field. For this release, the saved synthesis request matches the selected transcript and speaker, and each WAV passed structural checks. The audio has not been independently transcribed or human-rated; qastatus records that distinction. The matching source…
Independent publisher
Temporary Account
instinct1912
Models in Library0
Datasets in Library1
Models on Hugging Face3
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to speech.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.