Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Pooling Loss.
☆26Oct 11, 2024Updated 2 years ago
Alternatives and similar repositories for CE-OptimizedLoss
Users that are interested in CE-OptimizedLoss are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆60Sep 6, 2023Updated 3 years ago
- End-to-End Speech Processing Toolkit☆16Jan 20, 2025Updated last year
- Python implementation of CTC beam search decoder + agnostic LM scorer☆20Dec 16, 2020Updated 5 years ago
- A ctc decoder for both online and offline asr model☆66Nov 18, 2023Updated 3 years ago
- it's ASR decoder and make graph project☆33May 26, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Open Source WFST-based Decoder Toolkit☆76Feb 11, 2016Updated 10 years ago
- Dataset for Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models in Interspeech 2024.☆16Jul 4, 2024Updated 2 years ago
- The project for speech translation☆12Sep 28, 2023Updated 3 years ago
- ☆16Nov 26, 2024Updated last year
- An extension of thu-spmi/CAT which contains a full-fledged implementation of CTC-CRF for Tensorflow.☆12Jul 5, 2021Updated 5 years ago
- NAR-BERT-ASR☆10Sep 27, 2021Updated 5 years ago
- Implementation of the paper "Self-supervised Learning with Random-projection Quantizer for Speech Recognition" in Pytorch.☆97May 25, 2023Updated 3 years ago
- **ICASSP 2022** 《Toward Degradation-Robust Voice Conversion》Using speech enhancement and end-to-end denoising training to improve degrada…☆24Sep 27, 2022Updated 4 years ago
- ☆10Oct 20, 2022Updated 4 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [EMNLP 2026] Low-dimensional Unified Audio Tokenizer for Understanding and Generation☆23May 28, 2026Updated 5 months ago
- 实时语音 agent 架构手册。四种链路形态(级联 / 半级联 / S2S / 全双工)的取舍;判停、打断、首音、工具回合、会话恢复、音频前处理、评测七个机制的设计空间;pipecat、livekit-agents、TEN、unmute、moshi、Qwen3-Omni、C…☆21Oct 23, 2026Updated 3 weeks ago
- ☆21Jun 1, 2021Updated 5 years ago
- [SLT'24] Mamba-based Decoder-Only Approach for Speech Recognition☆19Dec 1, 2024Updated last year
- A KALDI/C++ implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆15Sep 4, 2019Updated 7 years ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆116Sep 2, 2026Updated 2 months ago
- An upgrade framework for train and validate compare with icefall using Lightning.☆16Mar 26, 2025Updated last year
- Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks https://arxiv.org/abs/19…☆14Apr 16, 2020Updated 6 years ago
- [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-…☆80Jul 14, 2026Updated 4 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Conversion of recurrent neural network language models to weighted finite state transducers☆58Jun 1, 2018Updated 8 years ago
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆54Dec 23, 2024Updated last year
- This repository is a curated list of awesome Speech Keyword Spotting (Wake-Up Word Detection).☆294May 23, 2022Updated 4 years ago
- We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction☆213Jul 17, 2026Updated 4 months ago
- ☆16Aug 25, 2022Updated 4 years ago
- Official source code for the paper "Tailored Design of Audio-Visual Speech Recognition Models using Branchformers"☆15Feb 24, 2025Updated last year
- ICASSP 2021 accepted papers in term of voice conversion (VC)☆18Apr 11, 2021Updated 5 years ago
- ☆37Jun 28, 2021Updated 5 years ago
- ☆12Feb 22, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆14Feb 3, 2026Updated 9 months ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Mar 19, 2024Updated 2 years ago
- Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.☆140Sep 25, 2023Updated 3 years ago
- ☆12Jun 16, 2018Updated 8 years ago
- ☆14Sep 7, 2025Updated last year
- Onnx wrapper for espnet infrernce model☆169Nov 11, 2026Updated last week
- CAT is more than a CRF-based ASR toolkit: it provides a complete workflow for data-efficient end-to-end ASR, supporting CTC, CTC-CRF, RNN…☆369Feb 5, 2026Updated 9 months ago
Are these results useful?