A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[Misc] Openai transcription client example use same Whisper model (#16487)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Apr 12, 2025 at 09:27 UTC
f069f3ea74a6436c5870f792d1dc0cc50ff74380
1 file changed
+1
-1
examples/online_serving/openai_transcription_client.py
+1
-1
@@ -23,7 +23,7 @@ def sync_openai():
23
with open(str(mary_had_lamb), "rb") as f:
24
transcription = client.audio.transcriptions.create(
25
file=f,
26
- model="openai/whisper-small",
26
+ model="openai/whisper-large-v3",
27
language="en",
28
response_format="json",
29
temperature=0.0)