[Voxtral Realtime] Change name (#33716)

Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>

examples/online_serving/openai_realtime_client.py

@@ -7,7 +7,7 @@ audio transcription by uploading an audio file.
 Before running this script, you must start the vLLM server with a realtime-capable
 model, for example:
 
-    vllm serve mistralai/Voxtral-Mini-3B-Realtime-2602 --enforce-eager
+    vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --enforce-eager
 
 Requirements:
 - vllm with audio support
@@ -126,7 +126,7 @@ if __name__ == "__main__":
     parser.add_argument(
         "--model",
         type=str,
-        default="mistralai/Voxtral-Mini-3B-Realtime-2602",
+        default="mistralai/Voxtral-Mini-4B-Realtime-2602",
         help="Model that is served and should be pinged.",
     )
     parser.add_argument(

examples/online_serving/openai_realtime_microphone_client.py

@@ -5,7 +5,7 @@ Minimal Gradio demo for real-time speech transcription using the vLLM Realtime A
 
 Start the vLLM server first:
 
-    vllm serve mistralai/Voxtral-Mini-3B-Realtime-2602 --enforce-eager
+    vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --enforce-eager
 
 Then run this script:
 
@@ -166,7 +166,7 @@ if __name__ == "__main__":
     parser.add_argument(
         "--model",
         type=str,
-        default="mistralai/Voxtral-Mini-3B-Realtime-2602",
+        default="mistralai/Voxtral-Mini-4B-Realtime-2602",
         help="Model that is served and should be pinged.",
     )
     parser.add_argument(

tests/entrypoints/openai/test_realtime_validation.py

@@ -24,7 +24,7 @@ MISTRAL_FORMAT_ARGS = [
     "mistral",
 ]
 
-MODEL_NAME = "mistralai/Voxtral-Mini-3B-Realtime-2602"
+MODEL_NAME = "mistralai/Voxtral-Mini-4B-Realtime-2602"
 
 
 def _audio_to_base64_pcm16(path: str, target_sr: int = 16000) -> str:

tests/models/multimodal/generation/test_voxtral_realtime.py

@@ -19,7 +19,7 @@ from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.inputs.data import TokensPrompt
 from vllm.v1.engine.async_llm import AsyncLLM, StreamingInput
 
-MODEL_NAME = "mistralai/Voxtral-Mini-3B-Realtime-2602"
+MODEL_NAME = "mistralai/Voxtral-Mini-4B-Realtime-2602"
 ENGINE_CONFIG = dict(
     model=MODEL_NAME,
     max_model_len=8192,