Kinyarwanda Orpheus v0.6 (Backup β NOT WORKING)
Status: NO CLEAR VOICE β This is a backup checkpoint only. Do not use for inference.
Details
- Base: vysakh25/Vysakh-Orpheus-3B-Kinyarwanda-v0.5 (merged)
- Data: AfriVoice 40K + Common Voice 5K (45K clips)
- Training: 21,000 steps (37%), loss 3.92, epoch 14.9
- Result: Partial speech on 1/3 test prompts (t2 only), very quiet, no consistent voice
Version Chain
v0.1 β v0.2 β v0.3 (first speech) β v0.4 (silent, batch too big) β v0.5 (best speech) β v0.6 (this, partial) β v0.7 (RBA data, training...)
- Downloads last month
- 50
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support