Files
vllm-omni/tests/dfx/perf/tests/test_tts.json
T

476 lines
11 KiB
JSON

[
{
"test_name": "test_qwen3_tts_base",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100",
"npu": "A3"
},
"num_cards": 2
}
},
"full_model",
"tts"
],
"server_params": {
"model": "Qwen/Qwen3-TTS-12Hz-1.7B-Base",
"stage_overrides": {
"1": {
"devices": "1"
}
}
},
"benchmark_params": [
{
"task": "voice_clone",
"eval_phase": "latency",
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "linyueqian/seed-tts-eval-subset",
"num_prompts": [
20
],
"max_concurrency": [
1
],
"seed_tts_locale": "en",
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
141.2791
],
"median_audio_rtf": [
0.1591
]
}
},
{
"task": "voice_clone",
"eval_phase": "throughput",
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "linyueqian/seed-tts-eval-subset",
"num_prompts": [
80,
128,
128
],
"max_concurrency": [
8,
16,
64
],
"seed_tts_locale": "en",
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
226.747,
647.1272,
4777.2714
],
"median_audio_rtf": [
0.3313,
0.3642,
1.2282
],
"audio_throughput": [
24.2296,
40.3552,
43.2572
]
}
},
{
"task": "voice_clone",
"eval_phase": "quality",
"enabled": false,
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "linyueqian/seed-tts-eval-subset",
"num_prompts": [
200
],
"max_concurrency": [
4
],
"seed_tts_locale": "en",
"seed_tts_wer_eval": true,
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_audio_rtf": [
0.45
]
}
}
]
},
{
"test_name": "test_qwen3_tts_customvoice",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 2
}
},
"full_model",
"tts"
],
"server_params": {
"model": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
"stage_overrides": {
"1": {
"devices": "1"
}
}
},
"benchmark_params": [
{
"task": "default_voice",
"eval_phase": "latency",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
20
],
"max_concurrency": [
1
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "Vivian",
"language": "English",
"task_type": "CustomVoice"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
46.8434
],
"median_audio_rtf": [
0.1367
]
}
},
{
"task": "default_voice",
"eval_phase": "throughput",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
80,
128,
128
],
"max_concurrency": [
8,
16,
64
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "Vivian",
"language": "English",
"task_type": "CustomVoice"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
75.3341,
713.7727,
5941.7179
],
"median_audio_rtf": [
0.1859,
0.3148,
1.1662
],
"audio_throughput": [
38.3858,
55.3523,
68.7032
]
}
},
{
"task": "default_voice",
"eval_phase": "quality",
"enabled": false,
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
200
],
"max_concurrency": [
4
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "Vivian",
"language": "English",
"task_type": "CustomVoice"
},
"seed_tts_wer_eval": true,
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_audio_rtf": [
0.35
]
}
},
{
"task": "default_voice",
"eval_phase": "stress",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
100
],
"request_rate": [
2.0
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "Vivian",
"language": "English",
"task_type": "CustomVoice"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
56.746
],
"median_audio_rtf": [
0.1571
],
"audio_throughput": [
11.1226
]
}
},
{
"task": "voice_design",
"eval_phase": "latency",
"dataset_name": "seed-tts-design",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_design",
"num_prompts": [
20
],
"max_concurrency": [
1
],
"seed_tts_locale": "en",
"extra_body": {
"task_type": "VoiceDesign",
"language": "English"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
46.3479
],
"median_audio_rtf": [
0.1352
]
}
},
{
"task": "voice_design",
"eval_phase": "throughput",
"dataset_name": "seed-tts-design",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_design",
"num_prompts": [
80,
128,
128
],
"max_concurrency": [
8,
16,
64
],
"seed_tts_locale": "en",
"extra_body": {
"task_type": "VoiceDesign",
"language": "English"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
75.5967,
587.5877,
4960.3726
],
"median_audio_rtf": [
0.1871,
0.3143,
1.1703
],
"audio_throughput": [
38.9378,
55.1846,
71.5708
]
}
},
{
"task": "voice_design",
"eval_phase": "stress",
"dataset_name": "seed-tts-design",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_design",
"num_prompts": [
100
],
"request_rate": [
2.0
],
"seed_tts_locale": "en",
"extra_body": {
"task_type": "VoiceDesign",
"language": "English"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
55.5029
],
"median_audio_rtf": [
0.1508
],
"audio_throughput": [
9.4885
]
}
}
]
},
{
"test_name": "test_voxtral_tts",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 1
}
},
"full_model",
"tts"
],
"server_params": {
"model": "mistralai/Voxtral-4B-TTS-2603"
},
"benchmark_params": [
{
"task": "default_voice",
"eval_phase": "latency",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
20
],
"max_concurrency": [
1
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
82.1886
],
"median_audio_rtf": [
0.1241
]
}
},
{
"task": "default_voice",
"eval_phase": "throughput",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
80
],
"max_concurrency": [
8
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
160.9168
],
"median_audio_rtf": [
0.1907
],
"audio_throughput": [
39.2332
]
}
},
{
"task": "default_voice",
"eval_phase": "stress",
"dataset_name": "seed-tts-text",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [
100
],
"request_rate": [
2.0
],
"seed_tts_locale": "en",
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
100.1265
],
"median_audio_rtf": [
0.1437
],
"audio_throughput": [
11.7605
]
}
}
]
}
]