GigaAM v3 e2e RNNT ONNX
Prepared runtime artifacts derived from upstream ai-sage/GigaAM-v3 revision
e2e_rnnt.
This repository contains exported ONNX runtime artifacts for the current
GigaAM v3_e2e_rnnt line, plus INT8 variants and a converted tokenizer JSON.
The source preparation flow uses a minimal vendored extraction of the upstream
RNNT model code to avoid depending on the full upstream runtime stack during
conversion and publication.
Repository ID: cnonim/gigaam-v3-e2e-rnnt-onnx
Included files:
onnx/v3_e2e_rnnt_encoder.onnxonnx/v3_e2e_rnnt_decoder.onnxonnx/v3_e2e_rnnt_encoder_int8.onnxonnx/v3_e2e_rnnt_decoder_int8.onnxonnx/v3_e2e_rnnt_tokenizer.json
Preparation notes:
- based on upstream
ai-sage/GigaAM-v3model artifacts - exported to ONNX encoder/decoder runtime files
- includes INT8-quantized encoder and decoder variants
- includes
tokenizer.jsonconverted from the upstream SentencePiece tokenizer - uses a reduced vendored conversion path focused on the RNNT export surface
This repository is limited to the current v3_e2e_rnnt line. Future model lines
are intentionally out of scope for this publication surface.
Model tree for cnonim/gigaam-v3-e2e-rnnt-onnx
Base model
ai-sage/GigaAM-v3