Niagara Automatic Speech Recognition

Niagara is a family of streaming ASR models optimized for local, real-time transcription. All processing runs on-device, with no cloud dependency.

Built on a State Space Model (SSM) architecture with attention, Niagara achieves 150ms average latency from first audio to first token. Models range from 8M to 38M parameters, enabling deployment on resource-constrained edge hardware while maintaining accuracy competitive with much larger models.

Key Features

• Real-time streaming: Processing begins as soon as the first audio is received, minimizing latency

• Private: All voice processing runs locally

• Small footprint, high accuracy: 4 to 6× smaller than transformers at equivalent accuracy, verified independently on the HuggingFace Open ASR Leaderboard

• Cascaded output: Fast path (~150ms latency) for real-time display, refined path (~1s) for higher accuracy

• Multi-language: English, Spanish, Chinese (Mandarin), Japanese, and Korean; additional languages available upon request

Premium Features

• Custom vocabulary (coming soon): Accurate identification of brand names, technical jargon, and domain- or application-specific words can be added without retraining the core ASR model

Models

Select a model based on your resource constraints. Larger models provide higher accuracy; smaller models run on more constrained hardware. All models accept raw 16 kHz mono PCM audio with no file headers and output punctuated, capitalized text.

		38M	19M	9M	8M
Languages	English	✓	✓	✓	✓
	Spanish	✓	—	—	✓
	Chinese (Mandarin)	✓	—	—	✓
	Japanese	✓	—	—	—
	Korean	✓	—	—	—
Sizes	32-bit	147MB	80MB	38MB	32MB
	8-bit	39MB	—	10MB	9MB

About the Name

ABR names its model families after rivers. State space models process sequential data as a continuous flow, always moving forward and maintaining state efficiently over time. The Niagara model family is named for the river in ABR’s home province of Ontario, Canada, whose falls have the highest flow rate in North America.