Search public pages, research tools, and SAVRN solutions.
Organization
ghanaopenai
Making AI accessible for Ghana
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Audio to audio.
Reported licenses: cc-by-nc-4.0. 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.
Voice conversion for Avatime (avn). An audio-to-audio model that converts speech into the Zephyr voice while preserving the language. This checkpoint is dedicated to Avatime: it was fine-tuned only on Avatime (avn) clips from starting from the zero-shot seed-uvit-whisper-small-wavenet base. Use it to convert audio in Avatime. For other languages — or as a cross-lingual fallback — use ghanaopenai/ghana-vc. The library auto-selects this model when the dataset/config name matches.
Voice conversion for Asante Twi (twi). An audio-to-audio model that converts speech into the Zephyr voice while preserving the language. This checkpoint is dedicated to Asante Twi: it was fine-tuned only on Asante Twi (twi) clips from starting from the zero-shot seed-uvit-whisper-small-wavenet base. Use it to convert audio in Asante Twi. For other languages — or as a cross-lingual fallback — use ghanaopenai/ghana-vc. The library auto-selects this model when the dataset/config name matches.
This is a high-fidelity voice-converted female benchmark dataset derived from ghananlpcommunity/ghana-speech and ghanaopenai/ghana-english-tts-clean2. - Up to 20.0 hours per language across 42 indigenous Ghanaian languages (~790 hours). - 50.0 hours of Ghanaian English (ghanaenglish subset) from studio podcast/speech recordings.