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

35 lines
1016 B
JSON

[
{
"test_name": "test_qwen3_tts",
"server_params": {
"model": "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"
},
"benchmark_params": [
{
"dataset_name": "random",
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"num_prompts": [
10,
40
],
"max_concurrency": [
1,
4
],
"random_input_len": 100,
"random_output_len": 100,
"extra_body": {
"voice": "Vivian",
"language": "English"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_audio_ttfp_ms": [6000, 6000],
"mean_audio_rtf": [0.3, 0.3]
}
}
]
}
]