Model artifact repository for the real_nepali_v0.4 Piper/VITS checkpoint.

This is an experimental punctuation-aware continuation of ampixa/real-nepali-v0.2-kala. It keeps the same six-speaker map and clear Nepali frontend direction, but adds explicit punctuation tokens to the model input:

Expected files:

Training run:

The remote path contains v0.3 because that is the internal punctuation-token frontend profile name. The release/evaluation label for this checkpoint is v0.4.

Checkpoint SHA-256:

Training mix:

Speaker IDs:

Important caveat: this checkpoint should be judged by listening. It was trained to test whether punctuation tokens improve prosody without repeating the quality loss seen in the earlier tiny synthetic-only v0.3 repair run. Use the punctuation review samples before treating it as the production/default model.