Text-to-Speech
Safetensors
PyTorch
Persian
persian
grainspeech
hifi-gan
experimental
single-speaker
Gooya-Microscopy-v2-exp / verification.json
Reza2kn's picture
Release self-contained experimental Persian TTS with verified offline CPU inference
4fb5649 verified
Raw
History Blame Contribute Delete
971 Bytes
{
"status": "passed",
"environment": "clean isolated Python venv; package copied into a temporary directory; empty HF cache; offline env flags; CPU inference",
"python": "3.13.11",
"sample_seconds": 17.391333333333332,
"sample_rate": 24000,
"sample_max_abs_delta_against_listened_reference": 0.0,
"sample_segments": 6,
"numeric_smoke_text": "\u0627\u0645\u0631\u0648\u0632 \u06f2\u06f4 \u0646\u0641\u0631 \u0622\u0645\u062f\u0646\u062f. \u0633\u0627\u0639\u062a \u06f3 \u0627\u0633\u062a.",
"numeric_smoke_seconds": 3.3613333333333335,
"checks": [
"strict safetensors state loading",
"exact architecture parameter count",
"nonempty finite audio",
"all G2P segments emitted EOS",
"requested sample waveform parity <1e-4",
"separate number-normalization inference"
],
"not_tested": [
"human accuracy of numeral sample",
"Windows/macOS/mobile runtime",
"FP16 or quantized inference",
"old-device latency"
]
}