If you’ve been looking for a way to bring powerful, reliable speech recognition to your local environment, without relying on external APIs, NVIDIA’s new Canary-Qwen-2.5B might be exactly what you need. With 2.5 billion parameters under the hood, this model doesn’t just transcribe English speech with near state-of-the-art accuracy, it does so with punctuation, capitalization, and ultra fast speed (418 RTFx). Canary-Qwen stands out with its two-in-one nature: in ASR mode, it delivers high-quality transcriptions; in LLM mode, it can go further, summarizing, answering questions, or post-processing transcripts using full language understanding. It’s fast, it’s flexible, and it’s designed for real-world, production-grade use.
In this article, we’ll walk you through how to get Canary-Qwen-2.5B up and running locally or in GPU-acclerated environments in minutes.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 1x RTX A6000
- Storage: 50 GB (preferable)
- VRAM: at least 16 GB
- Anaconda installed
Step-by-step process to install and run Canary-Qwen-2.5B
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n canary python=3.11 -y && conda activate canary
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch>=2.6.0 torchvision torchaudio
pip install einops timm pillow
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install sentencepiece bitsandbytes protobuf decord numpy
Output:
3. Install NVIDIA NeMo.
python -m pip install "nemo_toolkit[asr,tts] @ git+https://github.com/NVIDIA/NeMo.git"
4. Install some other required dependencies for audio processing.
sudo apt-get update
sudo apt-get install ffmpeg
pip install sacrebleu
5. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
6. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints, load it to GPU and configure prompt and load audio file.
import torch
import torchaudio
from nemo.collections.speechlm2.models import SALM
# Load the model
model = SALM.from_pretrained('nvidia/canary-qwen-2.5b')
# Load and preprocess the audio
waveform, sample_rate = torchaudio.load("speech.wav")
expected_sr = model.perception.preprocessor.featurizer.sample_rate
if sample_rate != expected_sr:
resampler = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=expected_sr)
waveform = resampler(waveform)
if waveform.dim() == 2:
waveform = waveform.mean(dim=0)
waveform = waveform.unsqueeze(0)
audio_lens = torch.tensor([waveform.shape[1]])
prompt = [[{"role": "user", "content": f"Transcribe the following: {model.audio_locator_tag}"}]]
answer_ids = model.generate(
prompts=prompt,
audios=waveform,
audio_lens=audio_lens,
max_new_tokens=128,
)
# Decode result
text = model.tokenizer.ids_to_text(answer_ids[0].tolist())
print(text)
Here’s the output for the given audio file:
Audio: https://drive.google.com/file/d/1u9583BT8pvQB_pmxHhrDlNDfVi8BTG4_/view?usp=sharing
Output:
Conclusion
We’ve covered everything from installing dependencies and loading the 2.5 B‑parameter Canary‑Qwen model locally or on GPU‑accelerated infrastructure, to managing audio preprocessing, transcription, and optional LLM post‑processing. What makes this setup rock-solid is pairing Canary‑Qwen with NodeShift AI infra. NodeShift offers affordable, scalable on‑demand GPU instances across global regions, automated deployment via Terraform or GitHub Actions, and enterprise‑grade compliance, so you can spin up an A100 or H100‑backed VM in minutes, run your transcription workflows and other AI workflows, and scale them securely and cost‑effectively.
