60 lines
1.4 KiB
JSON
60 lines
1.4 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": 2366.1640412174165,
|
|
"playback_start_ms": 2366.16463214159,
|
|
"stall_at_ttfa_ms": 0,
|
|
"audio_s": 4.48,
|
|
"total_s": 2.864769846200943,
|
|
"rtf": 0.6394575549555676,
|
|
"decode_ms_total": 686.854031868279,
|
|
"chunks": [
|
|
{
|
|
"idx": 0,
|
|
"t_ms": 2366.16463214159,
|
|
"arrival_ms": 2176.4274998568,
|
|
"frames": 25,
|
|
"samples": 48000,
|
|
"decode_ms": 189.63613593950868
|
|
},
|
|
{
|
|
"idx": 1,
|
|
"t_ms": 2630.5868341587484,
|
|
"arrival_ms": 2176.4274998568,
|
|
"frames": 25,
|
|
"samples": 48000,
|
|
"decode_ms": 264.40681982785463
|
|
},
|
|
{
|
|
"idx": 2,
|
|
"t_ms": 2863.4107299149036,
|
|
"arrival_ms": 2176.4274998568,
|
|
"frames": 6,
|
|
"samples": 11520,
|
|
"decode_ms": 232.81107610091567
|
|
}
|
|
],
|
|
"device": "cpu",
|
|
"wav": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-163326/client_1.wav",
|
|
"codes": "/data/zhoutaichang/embedding_infer/vllm-omni/benchmarks/tts/edge_results/codec_stream/20260909-163326/client_1.codes.npy"
|
|
} |