TTS-E1 try 2

Voice Failed

tts_e1_repro_b

Fine-tune of IndicF5 on Vāgdhenu chant, trained on A100 40GB (Google Cloud, spot). Started 9 Oct 2026, ended 9 Oct 2026.

Hypothesis

Second launch of TTS-E1, with the data staged as one archive.

What we learned

Stopped while preparing data: a bug in the step that summarises the prepared clips. Fixed and relaunched.

Scores

No scores published yet.

Curves

No training curves were published for this run.Its scores above are what it published.

Model

Preset
IndicF5
Parameters
—
Layers · heads · width
22 · 16 · 1,024

Data

Recordings
Vāgdhenu chant
Audio published
None: these voices stay internal

Compute

GPU
A100 40GB
Where
Google Cloud (spot)
Steps
— / 15,000
GPU hours
0.07
Cost
$0.09
Spot restarts
0

Lineage

gcpa100spotindicf5