Files
vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-163326/client_3.json
T

60 lines
1.5 KiB
JSON

{
"codec_start": {
"type": "codec.start",
"version": 1,
"utterance_index": 0,
"sentence_index": 0,
"sentence_text": "I can't believe how beautiful the sunset looks from up here on the mountain.",
"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": 67,
"ttfa_ms": 2623.2912791892886,
"playback_start_ms": 2623.2917830348015,
"stall_at_ttfa_ms": 0,
"audio_s": 5.36,
"total_s": 3.1137252133339643,
"rtf": 0.5809188830846949,
"decode_ms_total": 642.5018617883325,
"chunks": [
{
"idx": 0,
"t_ms": 2623.2917830348015,
"arrival_ms": 2470.173351932317,
"frames": 25,
"samples": 48000,
"decode_ms": 153.0545693822205
},
{
"idx": 1,
"t_ms": 2832.9488299787045,
"arrival_ms": 2470.173351932317,
"frames": 25,
"samples": 48000,
"decode_ms": 209.64194368571043
},
{
"idx": 2,
"t_ms": 3112.7667292021215,
"arrival_ms": 2470.173351932317,
"frames": 17,
"samples": 32640,
"decode_ms": 279.8053487204015
}
],
"device": "cpu",
"wav": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-163326/client_3.wav",
"codes": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-163326/client_3.codes.npy"
}