Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.baseten.co/llms.txt

Use this file to discover all available pages before exploring further.

Speech-to-text

​
Setup

To get started, sign into Baseten with Truss and then install the OpenAI SDK.
Sign in to Baseten
uvx truss login --browser
Install the OpenAI SDK
uv pip install openai
Qwen/Qwen3-ASR-1.7B is a 1.7B-parameter encoder-decoder model. This preset serves Qwen3-ASR on a single H100 40GB through vLLM, tuned for fast multilingual transcription.

Hardware

H100_40GB × 1

Engine

vLLM 0.18.0

Concurrency

256

​
Write the config

Create and move into the project directory: 
mkdir qwen3-asr-1.7b-latency && cd qwen3-asr-1.7b-latency
Then create a file named config.yaml and paste the following:
config.yaml
model_name: "model:qwen3-asr-1.7b preset:latency"
model_metadata:
  repo_id: Qwen/Qwen3-ASR-1.7B
  example_model_input:
    stream: false
    messages:
      - role: user
        content:
          - type: audio_url
            audio_url:
              url: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav
  tags:
    - openai-compatible
secrets:
  hf_access_token: null
weights:
  - source: "hf://Qwen/Qwen3-ASR-1.7B@main"
    mount_location: "/app/models/Qwen/Qwen3-ASR-1.7B"
    auth_secret_name: "hf_access_token"
base_image:
  image: vllm/vllm-openai:v0.18.0
docker_server:
  start_command: sh -c "vllm serve /app/models/Qwen/Qwen3-ASR-1.7B --gpu-memory-utilization 0.8 --host 0.0.0.0 --port 8000"
  readiness_endpoint: /health
  liveness_endpoint: /health
  predict_endpoint: /v1/chat/completions
  server_port: 8000
resources:
  accelerator: H100_40GB:1
  cpu: "1"
  memory: 10Gi
  use_gpu: true
requirements:
  - vllm[audio]
  - librosa
  - torch
  - torchaudio
  - pynvml
  - ffmpeg-python
system_packages:
  - python3.10-venv
  - ffmpeg
  - openmpi-bin
  - libopenmpi-dev
runtime:
  predict_concurrency: 256

​
Flags

The start_command passes these flags to the engine. Each one controls a runtime or serving behavior:
FlagValueWhat it does
--gpu-memory-utilization0.8Fraction of GPU memory vLLM may use for weights and KV cache.

​
Deploy

Push the config to Baseten: 
uvx truss push
You should see output similar to: 
✨ Model qwen3-asr-1.7b-latency was successfully pushed ✨
🪵 View logs for your deployment at https://app.baseten.co/models/abcd1234/logs/wxyz5678
Your model ID is the string after /models/ in the logs URL (abcd1234 in the example). Use it wherever you see {model_id} in the next section.

​
Call the model

Your deployment serves an OpenAI-compatible chat completions API at /v1/chat/completions that accepts audio inputs. Replace {model_id} with your model ID and make sure BASETEN_API_KEY is set. Send audio as an audio_url content item on a chat message. The model returns the transcription as the assistant message content.
main.py
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3-ASR-1.7B",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "audio_url",
                    "audio_url": {
                        "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
                    },
                }
            ],
        }
    ],
)

print(response.choices[0].message.content)