anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI/Build] Voxtral TTS Tests (#3738)

Browse Source 
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
This commit is contained in:
Clodagh Walsh authored and GitHub committed 2026-06-10 20:32:21 +08:00
1 parent 2fa4c7a4a9
commit aa92a3a35d
4 files changed
+159 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/tests/test_tts.json
+61
View File
@@ -339,5 +339,66 @@
}
}
]
},
{
"test_name": "test_voxtral_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": [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": "casual_male"},
"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": "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": [3000],
"median_audio_rtf": [0.25],
"audio_throughput": [4.0]
}
}
]
}
]