idiap / apam
APAM toolkit is built on PyTorch and provides recipes to adapt pretrained acoustic models with a variety of sequence discriminative training criterions.
☆14Updated 4 years ago
Alternatives and similar repositories for apam:
Users that are interested in apam are comparing it to the libraries listed below
- ☆16Updated 5 years ago
- ☆16Updated 2 years ago
- ☆22Updated 5 years ago
- CMU multilingual speech repository☆31Updated 2 years ago
- In this repository, I try to combine k2 with speechbrain to decode well and fastly.☆16Updated 2 years ago
- A SPMI Lab toolkit for language models.☆11Updated 7 years ago
- Multipurpose Multi Speaker Mixture Signal Generator☆44Updated last week
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Updated 6 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 6 months ago
- it's a train acoustics model code lib☆26Updated 4 years ago
- ☆48Updated 4 years ago
- GlottDNN vocoder and tools for training DNN excitation models☆32Updated 3 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 4 years ago
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Updated 4 years ago
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Updated 6 years ago
- ☆75Updated 2 years ago
- Web page for ISCA Special Interest Group: Robust Speech Processing (RoSP)☆11Updated last year
- End-to-end diarization loss☆22Updated 3 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 2 months ago
- This repository contains the Kaldi LF-MMI implementation of the paper "Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for…☆9Updated 2 years ago
- ☆31Updated last year
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- ☆16Updated 5 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆47Updated 7 months ago
- pytorch CTC implementation for ASR. Use eesen's fst decoder framework☆10Updated 4 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 4 years ago
- ☆34Updated 5 years ago
- Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation☆39Updated 4 years ago
- ☆36Updated 2 years ago