1ytic / open_stt_e2eLinks
PyTorch end-to-end speech recognition
☆49Updated 4 years ago
Alternatives and similar repositories for open_stt_e2e
Users that are interested in open_stt_e2e are comparing it to the libraries listed below
Sorting:
- Recurrent Neural Aligner☆50Updated 5 years ago
- Tensor2tensor experiment with SpecAugment☆46Updated 6 years ago
- Pytorch implementation of "Generalized End-to-End Loss for Speaker Verification"☆103Updated 6 years ago
- PyTorch Implementations for End-to-End Automatic Speech Recognition☆127Updated 6 years ago
- INTERSPEECH 2019 Tutorial Materials☆194Updated 4 years ago
- The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architec…☆45Updated 2 years ago
- ASR with PyTorch☆140Updated 6 years ago
- Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP …☆60Updated 5 years ago
- A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.☆136Updated 5 years ago
- Deep multi-metric learning for text-independent speaker verification☆24Updated 5 years ago
- A fully convolution-network for speech-to-text, built on pytorch.☆126Updated 5 years ago
- Discriminative Neural Clustering for Speaker Diarisation☆79Updated 3 years ago
- transformer for ASR-systerm (via tensorflow2.0)☆114Updated 6 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 5 years ago
- ☆38Updated 5 years ago
- ☆76Updated 3 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆30Updated 5 years ago
- Auto Segmentation Criterion (ASG) implemented in pytorch☆51Updated 4 years ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 5 years ago
- Use your data to create a speech recognition system in Kaldi. Fast.☆65Updated 5 years ago
- A better, faster, stronger version of the unbounded interleaved-state recurrent neural network (UIS-RNN)☆62Updated 5 years ago
- An implementation of RNN-Transducer loss in TF-2.0.☆46Updated 2 years ago
- A "Crowd-Built" continuously growing speech dataset with transcripts. The dataset contains multiple languages and is intended for anyone …☆42Updated 3 years ago
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆77Updated 4 years ago
- Speaker diarization based on Kaldi x-vectors, tuned for 16k microphone data☆95Updated 2 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆39Updated 5 years ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 3 years ago
- PyTorch implementation of a Time Delay Neural Network (TDNN)☆41Updated 6 years ago
- A lightweight library to compute Diarization Error Rate (DER).☆62Updated 2 years ago