paper-with-me

홈 › Papers

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer

2024-01-30 · Yifan Peng, Jinchuan Tian, William Chen, Siddhant Arora, Brian Yan, Yui Sudo, Muhammad Shakeel, Kwanghee Choi, Jiatong Shi, Xuankai Chang, Jee-weon Jung, Shinji Watanabe

Recent studies have highlighted the importance of fully open foundation models. The Open Whisper-style Speech Model (OWSM) is an initial step towards reproducing OpenAI Whisper using public data and open-source toolkits. However, previous versions of OWSM (v1 to v3) are still based on standard Transformer, which might lead to inferior performance compared to state-of-the-art speech encoder architectures. This work aims to improve the performance and efficiency of OWSM without additional data. We present a series of E-Branchformer-based models named OWSM v3.1, ranging from 100M to 1B parameters. OWSM v3.1 outperforms its predecessor, OWSM v3, in most evaluation benchmarks, while showing an improved inference speed of up to 25%. We further reveal the emergent ability of OWSM v3.1 in zero-shot contextual biasing speech recognition. We also provide a model trained on a subset of data with low license restrictions. We will publicly release the code, pre-trained models, and training logs.

📄 PDF Abstract BibTeX arXiv:2401.16658

Code (1)

espnet/espnet 공식 구현 pytorch

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

2025-05-31 · Yifan Peng, Shakeel Muhammad, Yui Sudo, William Chen 외

The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by i…

Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data

2023-09-25 · Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi 외

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech…

Speech RecognitionTranslation

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model

2025-10-28 · Chin-Jou Li, Kalvin Chang, Shikhar Bharadwaj, Eunjung Yeo 외 arxiv

Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-gr…

Speech Recognition

OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification

2024-02-20 · Yifan Peng, Yui Sudo, Muhammad Shakeel, Shinji Watanabe

There has been an increasing interest in large speech models that can perform multiple tasks in a single model. Such models usually adopt an encoder-decoder or decoder-only architecture due to their popularity and good p…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderHallucination+5

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models

2024-06-13 · Jinchuan Tian, Yifan Peng, William Chen, Kwanghee Choi 외

The Open Whisper-style Speech Model (OWSM) series was introduced to achieve full transparency in building advanced speech-to-text (S2T) foundation models. To this end, OWSM models are trained on 25 public speech datasets…

Language ModelingLanguage ModellingLarge Language ModelSpeech-to-Text