BigSSL

Closed weights Google,Apple 8B parameters January 2021

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Google,Apple
Organisation type
Industry,Industry
Country
United States of America
Published
10 January 2021
Authors
Yu Zhang, Daniel S. Park, Wei Han,James Qin, Anmol Gulati, Joel Shor, Aren Jansen, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Françoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang and Yonghui Wu

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Speech recognition (ASR), Audio classification

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
8B

"... we study the utility of large models, with the parameter count ranging from 600M to 8B..."

Training data
100,530,000,000 tokens

Sum all values in Table VII, and add 34k for English VAD, and 926k for English Youtube = 3116k hours Note this involves significant self-training: "Noisy student training (NST) [23], [41] is a self-training method where a teacher model generates pseudo-labels for a large unlabeled dataset, which is in turn used to train a student model with augmentation." 1 hour ~ 13,680 words 13680 * 3116000 = 42626880000

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

Figure 1 "In particular, on an ASR task with 34k hours of labeled data, by fine-tuning an 8 billion parameter pre-trained Conformer model we can match state-of-the-art (SoTA) performance with only 3% of the training data and significantly improve SoTA with the full training set"

Citations
204

Sources

Where this record came from and when it was last checked.

Reference
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
Last updated
25 May 2026

What the numbers mean

About this model

BigSSL was published by Google,Apple, in United States of America, in January 2021. The organisation is categorised as industry,Industry.

It works in Speech, and is recorded as doing speech recognition (ASR), Audio classification.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Around 100,530,000,000 tokens went into training it.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

BigSSL — common questions

01

What GPU do I need to run BigSSL?

None. BigSSL is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Is BigSSL open source?

No. BigSSL has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does BigSSL have?

BigSSL has 8B parameters. "... we study the utility of large models, with the parameter count ranging from 600M to 8B...". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

04

Who created BigSSL?

BigSSL was published by Google,Apple, based in United States of America, categorised as industry,Industry.

05

When was BigSSL released?

BigSSL was published in January 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is BigSSL used for?

BigSSL works in Speech, and is recorded as handling speech recognition (ASR), Audio classification. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.