Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
Not on the map. Why?
Abstract (arXiv)
We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using OpenSeq2Seq give state-of-the-art performance at 1.5-3x less training time. OpenSeq2Seq currently provides building blocks for models that solve a wide range of tasks including neural machine translation, automatic speech recognition, and speech synthesis.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 3; 2023: 4; 2024: 1; 2025: 1.
11 papers.
- 2023Transformers in Speech Processing: A Surveycited by 39
- 20228-bit Numerical Formats for Deep Neural Networkscited by 25
- 2023Training and inference of large language models using 8-bit floating pointcited by 20
- 2023Unit Scaling: Out-of-the-Box Low-Precision Trainingcited by 17
- 2021Inductive biases, pretraining and fine-tuning jointly account for brain responses to speechcited by 14
- 2024Collage: Light-Weight Low-Precision Strategy for LLM Trainingcited by 10
- 2022ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inferencecited by 9
- 2022Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognitioncited by 5
- 2023Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Personcited by 4
- 2021Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Modelscited by 0
- 2025Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacycited by 0
- 2025Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy30 Nov 2025
- 2024Collage: Light-Weight Low-Precision Strategy for LLM Training6 May 2024
- 2023Training and inference of large language models using 8-bit floating point29 Sep 2023
- 2023Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person23 May 2023
- 2023Transformers in Speech Processing: A Survey21 Mar 2023
- 2023Unit Scaling: Out-of-the-Box Low-Precision Training20 Mar 2023
- 2022Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition28 Nov 2022
- 2022ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference9 Sep 2022
- 20228-bit Numerical Formats for Deep Neural Networks6 Jun 2022
- 2021Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models5 Nov 2021
- 2021Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech25 Feb 2021