BlueMagpie-TTS / release_metadata.json
voidful's picture
Initial OpenFormosa release of BlueMagpie-TTS (rebrand from voidful; provenance refs preserved)
4e9e0e4 verified
Raw
History Blame Contribute Delete
1.5 kB
{
"format": "bluemagpie-pretrained",
"checkpoint": "step_0003900",
"files": [
"pytorch_model.bin",
"audiovae.pth",
"config.json",
"tokenizer.json",
"tokenizer_config.json",
"checkpoints/hung_yi_lee_speaker_centroids.pt"
],
"evaluation": {
"scope": "internal held-out evaluation",
"cer": 0.048101,
"wer": 0.05356,
"reference_baseline_cer": 0.114483,
"reference_baseline_wer": 0.148266
},
"recommended_generation_defaults": {
"cfg_value": 2.8,
"inference_timesteps": 9,
"max_len": 2000,
"retry_badcase": true,
"retry_badcase_max_times": 3,
"retry_badcase_ratio_threshold": 6.0,
"speaker_id": "hung_yi_lee",
"speaker_source_dataset": "voidful/hung-yi_lee",
"speaker_centroid_path": "checkpoints/hung_yi_lee_speaker_centroids.pt",
"speaker_centroid_sha256": "e1d4c95a4c33935ff1fee0ab47fa796dcc13908a183c60e9b02bc0a61c541c4c",
"speaker_centroid_dim": 192
},
"recommended_generation_defaults_source": {
"scope": "tts_hard_sentences_zh_500 + Breeze-ASR-25 normalized CER",
"sentences": "/home/voidful/tts_hard_sentences_zh_500.txt",
"asr_model": "MediaTek-Research/Breeze-ASR-25",
"conversion": "s2twp",
"normalized_cer": 0.09669792733863977,
"mixed_token_error_rate": 0.0911015155363644,
"char_errors": 1227,
"char_reference_length": 12689,
"evaluated_examples": 500,
"trial": "hy_cfg2p8_steps9",
"run": "hungyi_high_refine_hy_cfg2p8_steps9_20260620"
}
}