GigaAM v3 E2E RNNT Core ML
Source: https://github.com/salute-developers/GigaAM
Model: v3_e2e_rnnt
Upstream revision: 559d88d6b72541412743929f633a6ae7c9950b85
License: MIT
This artifact contains separate encoder, predictor, and joiner Float32 ML Programs. The application owns greedy RNNT decoding. Validation fixture audio is private and is not included.
- Downloads last month
- -
Model tree for vadimsuhanov/gigaam-v3-e2e-rnnt-coreml
Base model
ai-sage/GigaAM-v3