[Perf][NemotronVoiceChat] Fast defaults for all three deploy profiles: 2.8x offline, realtime full-duplex audio (#6354)

Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Yuekai ZhangandClaude Fable 5 authored and GitHub committed 2026-09-03 18:49:19 -07:00
1 parent e43c787544
commit 4179b0cae1
22 files changed
+2606 -195

No files matched your search

@@ -216,7 +216,10 @@ async def run(args: argparse.Namespace) -> dict[str, object]:
if args.expect_function_call
else (
client.events.count("response.audio.delta") >= args.minimum_audio_chunks
and (client.events.count("response.done") > completed_responses_at_commit)
and (
args.allow_incomplete_response
or client.events.count("response.done") > completed_responses_at_commit
)
)
)
),
@@ -227,7 +230,7 @@ async def run(args: argparse.Namespace) -> dict[str, object]:
if client.events.errors():
raise AssertionError(f"Realtime session emitted errors: {client.events.errors()}")
done_events = _events(client, "response.done")
if not args.expect_function_call:
if not args.expect_function_call and not args.allow_incomplete_response:
response = done_events[-1].get("response") if done_events else None
status = response.get("status") if isinstance(response, dict) else None
if status != "completed":
@@ -344,6 +347,17 @@ def parse_args(argv: Sequence[str] | None = None) -> argparse.Namespace:
parser.add_argument("--instructions", default=DEFAULT_INSTRUCTIONS)
parser.add_argument("--max-frames", type=int)
parser.add_argument("--minimum-audio-chunks", type=int, default=1)
parser.add_argument(
"--allow-incomplete-response",
action="store_true",
help=(
"Accept a session whose responses all completed before the final "
"commit. A realtime-paced pipeline delivers each turn's audio and "
"response.done as the turn happens, so the strict "
"done-after-commit gate only holds when delivery lags the frame "
"clock; use this flag when measuring latency on fast configs."
),
)
parser.add_argument("--minimum-audio-rms", type=float, default=1e-4)
parser.add_argument("--expect-function-call", action="store_true")
parser.add_argument("--expected-function-name", default="generate_random_number")