Model reference · open weights

w2v-bert-2.0

w2v-bert-2.0 is an open-weight embedding model from facebook, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings facebook 1 variants 2.2M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What w2v-bert-2.0 is

W2v-BERT 2.0 speech encoder We are open-sourcing our Conformer-based W2v-BERT 2.0 speech encoder as described in Section 3.2.1 of the paper, which is at the core of our Seamless models. This model was pre-trained on 4.5M hours of unlabeled audio data covering more than 143 languages. It requires finetuning to be used for downstream tasks such as Automatic Speech Recognition (ASR), or Audio Classification. This model and its training are supported by 🤗 Transformers, more on it in the docs. 🤗 Transformers usage This is a bare checkpoint without any modeling head, and thus requires finetuning to be used for downstream tasks such as ASR. You can however use it to extract audio embeddings from the top layer with this code snippet: To learn more about the model use, refer to the following resources: - its docs - a blog post showing how to fine-tune it on Mongolian ASR - a training script example Seamless Communication usage This model can be used in Seamless Communication, where it was released. Here's how to make a forward pass through the voice encoder, after having completed the installation steps:

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerfacebook
TypeEmbedding models
Parameters (lead)580M
Variants1
Runs withtransformers
Released2023-12-19
Popularity2.2M downloads / month
Likes227
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
w2v-bert-2.0580MBF16~1.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys w2v-bert-2-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (w2v-bert-2-0 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"w2v-bert-2-0","input":"text to embed"}'

Details

Languages, data & research

Languages

af am ar as az be bn bs bg ca cs zh cy da

Tags

transformers safetensors wav2vec2-bert feature-extraction af am ar as az be bn bs bg ca

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want w2v-bert-2.0 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms