Memory efficient transducer loss computation
-
Updated
Jun 10, 2022 - CMake
#
rnn-t
Here are 10 public repositories matching this topic...
Streaming on-device speech recognition for Android — NEON-accelerated FastConformer (32M params), cache-aware streaming with 80 ms look-ahead, no cloud. Powered by the VoxRT runtime.
android kotlin neon speech-recognition jni speech-to-text arm64 nemo asr ctc on-device offline-speech-recognition rnn-t streaming-asr fastconformer voxrt
-
Updated
Jul 2, 2026 - Kotlin
Streaming on-device speech recognition for iOS — NEON-accelerated, encrypted FastConformer (32M params), RTF 0.08–0.10 on iPhone 13 Pro Max. Built on the VoxRT custom Rust inference runtime. SwiftPM distribution.
swift ios real-time swift-package-manager speech-recognition spm nemo ctc on-device offline-speech-recognition rnn-t streaming-asr fastconformer voxrt
-
Updated
Jul 2, 2026 - Swift
A tutorial on how to train RNN-T from scratch with Whisper encoder
-
Updated
Mar 11, 2025 - Python
Streaming 가능한 RNN Transducer 모델을 PyTorch Lightning으로 구현해본다.
online pytorch automatic-speech-recognition korean speech-to-text streaming-audio rnn-transducer pytorch-lightning rnn-t
-
Updated
Dec 20, 2022 - Python
PyTorch Implementation of RNN-Transducer
-
Updated
Jun 19, 2021 - Python
Streaming, offline-first speech-recognition toolkit — fbank frontend, VAD, chunked encoder, CTC/RNN-T decoding with LM fusion, WER/RTF scoring. NumPy/SciPy reference kernels, optional PyTorch backend.
-
Updated
Aug 1, 2026 - Python
Unofficial, From-scratch PyTorch replication of the Conformer paper (Gulati et al., 2020) — encoder, RNN-T decoder, training loop, and NeMo weight validation. Built block by block with documented maths.
deep-learning pytorch transformer speech-recognition attention convolution asr conformer rnn-t paper-replication
-
Updated
Mar 28, 2026 - Python
ASR (Speech to Text) in Bengali
pytorch bengali batch-processing audio-processing asr tokenization rnn-transducer pytorch-lightning rnn-t
-
Updated
Dec 26, 2023 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the rnn-t topic, visit your repo's landing page and select "manage topics."