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:
Accès en ligne:https://arxiv.org/abs/2509.14128
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914055573209088
author Sekoyan, Monica
Koluguri, Nithin Rao
Tadevosyan, Nune
Zelasko, Piotr
Bartley, Travis
Karpov, Nikolay
Balam, Jagadeesh
Ginsburg, Boris
author_facet Sekoyan, Monica
Koluguri, Nithin Rao
Tadevosyan, Nune
Zelasko, Piotr
Bartley, Travis
Karpov, Nikolay
Balam, Jagadeesh
Ginsburg, Boris
contents This report introduces Canary-1B-v2, a fast, robust multilingual model for Automatic Speech Recognition (ASR) and Speech-to-Text Translation (AST). Built with a FastConformer encoder and Transformer decoder, it supports 25 languages primarily European. The model was trained on 1.7M hours of total data samples, including Granary and NeMo ASR Set 3.0, with non-speech audio added to reduce hallucinations for ASR and AST. We describe its two-stage pre-training and fine-tuning process with dynamic data balancing, as well as experiments with an nGPT encoder. Results show nGPT scales well with massive data, while FastConformer excels after fine-tuning. For timestamps, Canary-1B-v2 uses the NeMo Forced Aligner (NFA) with an auxiliary CTC model, providing reliable segment-level timestamps for ASR and AST. Evaluations show Canary-1B-v2 outperforms Whisper-large-v3 on English ASR while being 10x faster, and delivers competitive multilingual ASR and AST performance against larger models like Seamless-M4T-v2-large and LLM-based systems. We also release Parakeet-TDT-0.6B-v3, a successor to v2, offering multilingual ASR across the same 25 languages with just 600M parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14128
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
Sekoyan, Monica
Koluguri, Nithin Rao
Tadevosyan, Nune
Zelasko, Piotr
Bartley, Travis
Karpov, Nikolay
Balam, Jagadeesh
Ginsburg, Boris
Computation and Language
Audio and Speech Processing
This report introduces Canary-1B-v2, a fast, robust multilingual model for Automatic Speech Recognition (ASR) and Speech-to-Text Translation (AST). Built with a FastConformer encoder and Transformer decoder, it supports 25 languages primarily European. The model was trained on 1.7M hours of total data samples, including Granary and NeMo ASR Set 3.0, with non-speech audio added to reduce hallucinations for ASR and AST. We describe its two-stage pre-training and fine-tuning process with dynamic data balancing, as well as experiments with an nGPT encoder. Results show nGPT scales well with massive data, while FastConformer excels after fine-tuning. For timestamps, Canary-1B-v2 uses the NeMo Forced Aligner (NFA) with an auxiliary CTC model, providing reliable segment-level timestamps for ASR and AST. Evaluations show Canary-1B-v2 outperforms Whisper-large-v3 on English ASR while being 10x faster, and delivers competitive multilingual ASR and AST performance against larger models like Seamless-M4T-v2-large and LLM-based systems. We also release Parakeet-TDT-0.6B-v3, a successor to v2, offering multilingual ASR across the same 25 languages with just 600M parameters.
title Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2509.14128