BigSSL
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
- Training data
- 100,530,000,000 tokens
"... we study the utility of large models, with the parameter count ranging from 600M to 8B..."
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
- Citations
- 204
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"
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 the country recorded as United States of America, during January 2021. The publishing organisation is categorised as industry,Industry.
It works in the domain of Speech, and is recorded as performing the task of 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
Training consumed a corpus of around 100,530,000,000 tokens of text.
The reason it appears in this catalogue at all: sOTA improvement.
Answers
BigSSL — common questions
BigSSL— what GPU do I need to run it?
None. This 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.
BigSSL— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
BigSSL— how many parameters does it have?
It has a parameter count of 8B. "... 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.
BigSSL— who created it?
It was published by Google,Apple, based in United States of America, an organisation categorised as industry,Industry.
BigSSL— when was it released?
It 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.
BigSSL— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of 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.
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.