IndexTTS2 Finetuning on IMDA NSC FEMALE_01

60-second takeaway
IndexTTS2 gave us a usable full-SFT baseline with strong operational predictability once we stabilized restart behavior.
In this run, model_step14000.pth was the practical checkpoint to keep.
The major challenge was process reliability and checkpoint retention policy, not core output quality.

Where this fits

• For founders: IndexTTS2 is a steady full-finetune option in this benchmark.
• For engineers: this page focuses on run recovery and checkpoint management as much as quality.

Series overview:

• https://instavar.com/blog/IMDA_NSC_Voice_Cloning_Finetuning_Benchmark_2026

Experiment setup

• Model: IndexTTS2
• Dataset: IMDA NSC FEMALE_01_44k processed manifests
• Hardware: RTX 3090 Ti 24 GB
• Training mode: full SFT with resume

Best checkpoint logic

• Best validation region was around step ~13800.
• Saved checkpoints available around that region were model_step14000.pth and later model_step15949.pth.
• We treated model_step14000.pth as the practical best anchor for this run.

Audio evidence

Representative sample

Settings: long-text prompt comparison path, step 14000 checkpoint.

Failure modes we saw

• Training runs were interrupted multiple times and required explicit resume management.
• Some crashes were low-level (pt_autograd_0 segfault signs), which made clean logs critical.
• Retention policy kept only recent checkpoint windows, so older steps disappeared automatically.

Recommended inference settings

• Keep checkpoint selection tied to both listening and nearest validation region.
• Prefer explicit run logs and resume metadata over implicit state.
• For this run, compare step 14000 and step 15949 only when you need late-run style differences.

Engineer appendix

Key paths from this run

• Checkpoints: /mnt/work/chee-wei-jie/voice-models/FEMALE_01_44k/trained_ckpts_female01