Image de couverture de livre

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sekoyan, Monica, Koluguri, Nithin Rao, Tadevosyan, Nune, Zelasko, Piotr, Bartley, Travis, Karpov, Nikolay, Balam, Jagadeesh, Ginsburg, Boris
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Audio and Speech Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation
par: Koluguri, Nithin Rao, et autres
Publié: (2024)

Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
par: Dhawan, Kunal, et autres
Publié: (2024)

BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5
par: Chen, Zhehuai, et autres
Publié: (2024)

Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
par: Wang, Weiqing, et autres
Publié: (2025)

Training and Inference Efficiency of Encoder-Decoder Speech Models
par: Żelasko, Piotr, et autres
Publié: (2025)

Granary: Speech Recognition and Translation Dataset in 25 European Languages
par: Koluguri, Nithin Rao, et autres
Publié: (2025)

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
par: Srivastav, Vaibhav, et autres
Publié: (2025)

META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR
par: Wang, Jinhan, et autres
Publié: (2024)

Less is More: Accurate Speech Recognition & Translation without Web-Scale Data
par: Puvvada, Krishna C., et autres
Publié: (2024)

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization
par: Andrusenko, Andrei, et autres
Publié: (2026)

Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages
par: Ayrapetyan, Alexan, et autres
Publié: (2025)

HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
par: Xu, Hainan, et autres
Publié: (2024)

Flexible Multichannel Speech Enhancement for Noise-Robust Frontend
par: Jukić, Ante, et autres
Publié: (2024)

Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
par: Park, Taejin, et autres
Publié: (2024)

NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks
par: Huang, He, et autres
Publié: (2024)

Unified Semi-Supervised Pipeline for Automatic Speech Recognition
par: Tadevosyan, Nune, et autres
Publié: (2025)

Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text
par: Xu, Hainan, et autres
Publié: (2026)

Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer
par: Burchi, Maxime, et autres
Publié: (2024)

Chain-of-Thought Prompting for Speech Translation
par: Hu, Ke, et autres
Publié: (2024)

Schrödinger Bridge for Generative Speech Enhancement
par: Jukić, Ante, et autres
Publié: (2024)

EMMeTT: Efficient Multimodal Machine Translation Training
par: Żelasko, Piotr, et autres
Publié: (2024)

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
par: Peng, Yifan, et autres
Publié: (2024)

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
par: Hu, Ke, et autres
Publié: (2025)

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition
par: Noroozi, Vahid, et autres
Publié: (2023)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
par: Wang, Weiqing, et autres
Publié: (2024)

Romanization Encoding For Multilingual ASR
par: Ding, Wen, et autres
Publié: (2024)

Instruction Data Generation and Unsupervised Adaptation for Speech Language Models
par: Noroozi, Vahid, et autres
Publié: (2024)

Enabling ASR for Low-Resource Languages: A Comprehensive Dataset Creation Approach
par: Yeroyan, Ara, et autres
Publié: (2024)

Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic
par: Grigoryan, Lilit, et autres
Publié: (2025)

Anticipating Future with Large Language Model for Simultaneous Machine Translation
par: Ouyang, Siqi, et autres
Publié: (2024)

Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
par: Langman, Ryan, et autres
Publié: (2024)

Breeding Season and Productivity of Monk Parakeets in Cordoba, Argentina
par: Navarro, Joaquín L, et autres
Publié: (1992)

Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering
par: Medennikov, Ivan, et autres
Publié: (2025)

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
par: Grigoryan, Lilit, et autres
Publié: (2025)

A Chat About Boring Problems: Studying GPT-based text normalization
par: Zhang, Yang, et autres
Publié: (2023)

How I Built ASR for Endangered Languages with a Spoken Dictionary
par: Bartley, Christopher, et autres
Publié: (2025)

GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
par: Aizman, Alex, et autres
Publié: (2026)

SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription
par: Grossman, Raymond, et autres
Publié: (2025)

ESBMC v7.6: Enhanced Model Checking of C++ Programs with Clang AST
par: Li, Xianzhiyu, et autres
Publié: (2024)

Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
par: Majumdar, Somshubra, et autres
Publié: (2024)