[CI] Align MiniMax H3 Ref2VA inputs and add I2VA/Ref2VA accuracy coverage (#5978)

Signed-off-by: david6666666 <530634352@qq.com>
This commit is contained in:
WeiQing Chen authored and GitHub committed 2026-08-11 13:36:37 +08:00
1 parent 4f9b65074d
commit 1f65814fab
8 files changed
+535 -262

No files matched your search

+5
View File
@@ -188,6 +188,11 @@ def mux_video_audio_bytes(
raise ValueError("Audio samples were not prepared for muxing.")
audio_frame = av.AudioFrame.from_ndarray(samples, format="fltp", layout=layout)
audio_frame.sample_rate = audio_sample_rate
# AAC has a one-frame encoder delay. Mark the input waveform as
# starting at t=0 so the MP4 muxer writes the corresponding negative
# priming timestamp instead of exposing the delay as leading silence.
audio_frame.pts = 0
audio_frame.time_base = Fraction(1, audio_sample_rate)
for packet in a_stream.encode(audio_frame):
container.mux(packet)
for packet in a_stream.encode():