minpeter / Voxtral-Mini-3B-2507

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?")
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 speaker who is more inspiring is the one who delivered the farewell address, as they express
# gratitude, optimism, and a strong commitment to the nation and its citizens. They emphasize the importance of
# self-government and active citizenship, encouraging everyone to participate in the democratic process. In contrast,
# the other speaker provides a factual update on the weather in Barcelona, which is less inspiring as it
# lacks the emotional and motivational content of the farewell address.

# **Differences:**
# - The farewell address speaker focuses on the values and responsibilities of citizenship, encouraging active participation in democracy.
# - The weather update speaker provides factual information about the temperature in Barcelona, without any emotional or motivational content.


messages = [
    user_msg,
    AssistantMessage(content=content).to_openai(),
    UserMessage(content="Ok, now please summarize the content of the first audio.").to_openai()
]
print(30 * "=" + "USER 2" + 30 * "=")
print(messages[-1]["content"])
print("\n\n")

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=0.2,
    top_p=0.95,
)
content = response.choices[0].message.content
print(30 * "=" + "BOT 2" + 30 * "=")
print(content)

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 transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3",
            },
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
            {"type": "text", "text": "What sport and what nursery rhyme are referenced?"},
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
            },
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
            },
            {"type": "text", "text": "Describe briefly what you can hear."},
        ],
    },
    {
        "role": "assistant",
        "content": "The audio begins with the speaker delivering a farewell address in Chicago, reflecting on his eight years as president and expressing gratitude to the American people. The audio then transitions to a weather report, stating that it was 35 degrees in Barcelona the previous day, but the temperature would drop to minus 20 degrees the following day.",
    },
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
            {"type": "text", "text": "Ok, now compare this new audio with the previous one."},
        ],
    },
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Why should AI models be open-sourced?",
            },
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversations = [
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
                },
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
                },
                {
                    "type": "text",
                    "text": "Who's speaking in the speach and what city's weather is being discussed?",
                },
            ],
        }
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
                },
                {"type": "text", "text": "What can you tell me about this audio?"},
            ],
        }
    ],
]

inputs = processor.apply_chat_template(conversations)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated responses:")
print("=" * 80)
for decoded_output in decoded_outputs:
    print(decoded_output)
    print("=" * 80)

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Mini-3B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

inputs = processor.apply_transcription_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated responses:")
print("=" * 80)
for decoded_output in decoded_outputs:
    print(decoded_output)
    print("=" * 80)