#!/usr/bin/env bash
# Retrain the 8k Snake-HiFiGAN vocoder on the FULL diverse corpus (~21k, zh+en mark voice),
# longer + higher MR-STFT weight -> crisper, less-buzzy 8kHz audio (raises the GT-mel->audio ceiling).
set -e
ZT=/home/luigi/jetson-tts/mossnano/zhtw8k; LOG=$ZT/voc_retrain.log
TRAIN=/home/luigi/moss-train-venv/bin/python
exec >>"$LOG" 2>&1
echo "===== VOC RETRAIN START $(date) ====="
cd /tmp/inflect-nano
CUDA_VISIBLE_DEVICES=1 $TRAIN -m inflect_nano.vocoder --train-jsonl $ZT/bili_voc_rows.jsonl \
  --out-dir $ZT/bili_vocoder_8k --variant snake_8k --steps 40000 --batch-size 16 \
  --segment-size 8192 --min-seconds 0.8 --max-seconds 20 --num-workers 4 --stft-weight 2.5 \
  --save-interval 5000 --log-interval 200 --device cuda
echo "===== VOC RETRAIN DONE $(date) ====="