Files
vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-164759/client_1.json
T

84 lines
1.9 KiB
JSON

{
"codec_start": {
"type": "codec.start",
"version": 1,
"utterance_index": 0,
"sentence_index": 0,
"sentence_text": "She said she would be here by noon, but nobody showed up.",
"model": "Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice",
"codebooks": 16,
"codebook_size": 2048,
"frame_rate_hz": 12.5,
"sample_rate": 24000,
"decoder_id": "qwen3_tts_tokenizer_v2_12hz",
"header_format": "<IHB"
},
"schedule": [
2,
4,
8,
16,
25
],
"total_frames": 56,
"ttfa_ms": 156.36097872629762,
"playback_start_ms": 156.36132610961795,
"stall_at_ttfa_ms": 0,
"audio_s": 4.48,
"total_s": 2.4820523858070374,
"rtf": 0.5540295504033566,
"decode_ms_total": 775.7537220604718,
"chunks": [
{
"idx": 0,
"t_ms": 156.36132610961795,
"arrival_ms": 108.53844881057739,
"frames": 2,
"samples": 3840,
"decode_ms": 47.80319286510348
},
{
"idx": 1,
"t_ms": 309.7477317787707,
"arrival_ms": 254.71370993182063,
"frames": 4,
"samples": 7680,
"decode_ms": 55.00476807355881
},
{
"idx": 2,
"t_ms": 619.3297319114208,
"arrival_ms": 539.5850511267781,
"frames": 8,
"samples": 15360,
"decode_ms": 79.70938924700022
},
{
"idx": 3,
"t_ms": 1238.8015231117606,
"arrival_ms": 1112.3944609425962,
"frames": 16,
"samples": 30720,
"decode_ms": 126.3788677752018
},
{
"idx": 4,
"t_ms": 2270.256470888853,
"arrival_ms": 2013.8698387891054,
"frames": 25,
"samples": 48000,
"decode_ms": 256.3534560613334
},
{
"idx": 5,
"t_ms": 2481.054992880672,
"arrival_ms": 2270.534466020763,
"frames": 1,
"samples": 1920,
"decode_ms": 210.50404803827405
}
],
"device": "cpu",
"wav": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-164759/client_1.wav",
"codes": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-164759/client_1.codes.npy"
}