Stt_ar_fastconformer_hybrid_large_pcd_v1.0
NVIDIA's Stt_ar_fastconformer_hybrid_large_pcd_v 1.0 is an open-source audio model exceling at transcribing Arabic speech into text with punctuation and diacritical marks support. It utilizes a FastConformer architecture with a hybrid Transducer and Connectionist Temporal Classification loss setup, and has around 115M parameters.
Input
Output
Context
-
Max Output
-
Parameters
115M
Technical Specifications
Model TypeAudio
Context WindowNot available
Max Output TokensNot available
Parameters115M
Release DateDec 25, 2024
Training CutoffNot available
Licensecc-by-4.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Stt_ar_fastconformer_hybrid_large_pcd_v1.0
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.