Run Nemotron Speech ASR on Novita

What is NVIDIA NeMo

NVIDIA NeMo Framework is a scalable and cloud-native generative AI framework built for researchers and PyTorch developers working on Large Language Models (LLMs), Multimodal Models (MMs), Automatic Speech Recognition (ASR), Text to Speech (TTS), and Computer Vision (CV) domains. It is designed to help you efficiently create, customize, and deploy new generative AI models by leveraging existing code and pre-trained model checkpoints.

For technical documentation, please see the NeMo Framework User Guide.

You can check the details on the official website of the project.

Run NVIDIA NeMo on Novita

Step 1: Console Entry
Launch the GPU interface and select Get Started to access deployment management.
Step 2: Package Selection
Locate Nemotron Speech ASR in the template repository and begin installation sequence.
Step 3: Infrastructure Setup
Configure computing parameters including memory allocation, storage requirements, and network settings. Select Deploy to implement.
Step 4: Review and Create
Double-check your configuration details and cost summary. When satisfied, click Deploy to start the creation process.
Step 5: Wait for Creation
After initiating deployment, the system will automatically redirect you to the instance management page. Your instance will be created in the background.
Step 6: Monitor Download Progress
Track the image download progress in real-time. Your instance status will change from Pulling to Running once deployment is complete. You can view detailed progress by clicking the arrow icon next to your instance name. Step 7: Verify Instance Status
Click the Logs button to view instance logs and confirm that the InvokeAI service has started properly.

How to get started

Install dependencies

1apt-get update && apt-get install -y libsndfile1 ffmpeg 
2pip install Cython packaging
3pip install git+https://github.com/NVIDIA/NeMo.git@main#egg=nemo_toolkit[asr]

The test script uses the official library example: https://github.com/NVIDIA-NeMo/NeMo/blob/main/examples/asr/asrcache_aware_streaming/speech_to_text_cache_aware_streaminginfer.py

1python speech_to_text_cache_aware_streaminginfer.py \
2    model_path=/yourPath/nemotron-speech-streaming-en-0.6b/nemotron-speech-streaming-en-0.6b.nemo \
3    audio_file=/yourPath/audio.wav

Parameter Description: model_path: Model parameter file audio_file: Audio stream file

Example: model_path: Download model here

audio_file: your audio_file

The following model output will be obtained:

1[NeMo I 2026-01-09 08:13:32 speech_to_text_cache_aware_streaming_infer:282] Final streaming transcriptions: ['The English forwarded to the French baskets of flowers of which they had made a plentiful provision to greet the arrival of the young princess. The French, in return, invited the English to a supper, which was to be given the next day.']

The model has converted the audio stream to text.