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

192 lines
6.4 KiB
JSON

[
{
"test_name": "test_qwen3_tts_base",
"server_params": {
"model": "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
},
"benchmark_params": [
{
"task": "voice_clone",
"eval_phase": "latency",
"enabled": false,
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"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": [350],
"median_audio_rtf": [0.25]
}
},
{
"task": "voice_clone",
"eval_phase": "throughput",
"enabled": false,
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"num_prompts": [80],
"max_concurrency": [8],
"seed_tts_locale": "en",
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [3500],
"median_audio_rtf": [0.75],
"audio_throughput": [10.0]
}
},
{
"task": "voice_clone",
"eval_phase": "quality",
"enabled": false,
"dataset_name": "seed-tts",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"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",
"server_params": {
"model": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"
},
"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": [150],
"median_audio_rtf": [0.15]
}
},
{
"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": "Vivian", "language": "English", "task_type": "CustomVoice"},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [1500],
"median_audio_rtf": [0.30],
"audio_throughput": [30.0]
}
},
{
"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": [3000],
"median_audio_rtf": [0.25],
"audio_throughput": [4.0]
}
},
{
"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": [150],
"median_audio_rtf": [0.15]
}
},
{
"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],
"max_concurrency": [8],
"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": [1500],
"median_audio_rtf": [0.35],
"audio_throughput": [25.0]
}
},
{
"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": [3500],
"median_audio_rtf": [0.30],
"audio_throughput": [4.0]
}
}
]
}
]