Voxtral-Small-24B-2507

uv pip install -U "vllm[audio]" --system

python -c "import mistral_common; print(mistral_common.__version__)"

git clone https://github.com/vllm-project/vllm && cd vllm

python examples/offline_inference/audio_language.py --num-audios 2 --model-type voxtral

pip install --upgrade mistral_common\[audio\]

from mistral_common.protocol.instruct.messages import TextChunk, AudioChunk, UserMessage, AssistantMessage, RawAudio
from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset")
bcn_file = hf_hub_download("patrickvonplaten/audio_samples", "bcn_weather.mp3", repo_type="dataset")

def file_to_chunk(file: str) -> AudioChunk:
    audio = Audio.from_file(file, strict=False)
    return AudioChunk.from_audio(audio)

text_chunk = TextChunk(text="Which speaker is more inspiring? Why? How are they different from each other? Answer in French.")
user_msg = UserMessage(content=[file_to_chunk(obama_file), file_to_chunk(bcn_file), text_chunk]).to_openai()

print(30 * "=" + "USER 1" + 30 * "=")
print(text_chunk.text)
print("\n\n")

response = client.chat.completions.create(
    model=model,
    messages=[user_msg],
    temperature=0.2,
    top_p=0.95,
)
content = response.choices[0].message.content

print(30 * "=" + "BOT 1" + 30 * "=")
print(content)
print("\n\n")
# The model could give the following answer:
#

from mistral_common.protocol.transcription.request import TranscriptionRequest
from mistral_common.protocol.instruct.messages import RawAudio
from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset")
audio = Audio.from_file(obama_file, strict=False)

audio = RawAudio.from_audio(audio)
req = TranscriptionRequest(model=model, audio=audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))

response = client.audio.transcriptions.create(**req)
print(response)

from mistral_common.protocol.instruct.messages import AudioChunk, UserMessage, TextChunk
from mistral_common.protocol.transcription.request import TranscriptionRequest
from mistral_common.protocol.instruct.tool_calls import Function, Tool

from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

tool = Tool(
    function=Function(
        name="get_current_weather",
        description="Get the current weather",
        parameters={
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "format": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"],
                    "description": "The temperature unit to use. Infer this from the user's location.",
                },
            },
            "required": ["location", "format"],
        },
    )
)
tools = [tool.to_openai()]


weather_like = hf_hub_download("patrickvonplaten/audio_samples", "fn_calling.wav", repo_type="dataset")

def file_to_chunk(file: str) -> AudioChunk:
    audio = Audio.from_file(file, strict=False)
    return AudioChunk.from_audio(audio)

audio_chunk = file_to_chunk(weather_like)

print(30 * "=" + "Transcription" + 30 * "=")
req = TranscriptionRequest(model=model, audio=audio_chunk.input_audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))
response = client.audio.transcriptions.create(**req)
print(response.text) # How is the weather in Madrid at the moment?
print("\n")


print(30 * "=" + "Function calling" + 30 * "=")
audio_chunk = file_to_chunk(weather_like)
user_msg = UserMessage(content=[audio_chunk]).to_openai()
response = client.chat.completions.create(
    model=model,
    messages=[user_msg],
    temperature=0.2,
    top_p=0.95,
    tools=[tool.to_openai()]
)
print(30 * "=" + "BOT 1" + 30 * "=")
print(response.choices[0].message.tool_calls)
print("\n\n")

pip install -U transformers

pip install --upgrade "mistral-common[audio]"