Irodori-TTS tested by Argusic Runner
Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100
all runs of Irodori-TTSdiffusion-modelsflow-matchingpythonspeech-synthesistext-to-speechtts
Session recording
Download the original recording · fingerprint 1b54d54b682b9072...
What the test found
uv sync --extra cpu installed all 200+ dependencies including torch 2.10.0+cpu, dacvae, silentcipher, transformers 5.12.1, safely. All 15 irodori_tts sub-modules import cleanly. The full InferenceRuntime pipeline loads a checkpoint, loads the DACVAE codec (107M params) from HF Hub, tokenizes text, runs the RF DiT forward pass (309K-param toy model), decodes latents, applies SilentCipher watermarking, and writes a 48kHz WAV that ffmpeg validates as valid audio. The 7 CLI scripts and 20 training configs all parse correctly.
Argusic installed Irodori-TTS in 5 minutes and launched it; verification reached Verified with mock services. 3 of 3 recorded errors were worked through (see the timeline below).
Runs with mocksall runs of Irodori-TTS
This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.
Error and fix timeline
No errors were recorded for this run.