6122a678f5
Refactors and extends model export support to include new NeMo Parakeet TDT int8 variants for English and Japanese, updating the Kotlin API, export scripts, test runners, and CI workflows. - Added support for two new int8 model types in OfflineRecognizer.kt. - Enhanced Python export scripts to perform dynamic quantization and metadata injection. - Updated shell scripts and GitHub workflows to package, test, and publish int8 model artifacts.
Introduction
This folder contains scripts for exporting models from
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_fastconformer_ctc_large
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_enes_conformer_transducer_large_codesw
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_fastconformer_transducer_large
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_enzh_fastconformer_transducer_large_codesw
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_fa_fastconformer_hybrid_large
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_it_fastconformer_hybrid_large_pc
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_pl_fastconformer_hybrid_large_pc
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_ua_fastconformer_hybrid_large_pc
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_fastconformer_hybrid_large_pc
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_es_fastconformer_hybrid_large_pc
-
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/parakeet-tdt_ctc-110m
to sherpa-onnx.