Model reference · open weights
wav2vec2-large-100k-voxpopuli is an open-weight audio or speech model from Meta. wav2vec2-large-100k-voxpopuli (BF16) weighs 1.3 GB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the facebook/wav2vec2-large-100k-voxpopuli model card, 2026-10-01
What it is
| Released by | Meta |
|---|---|
| Released | 2022-03-02 |
| VRAM | 1.3 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Facebook's Wav2Vec2 large model pretrained on the 100k unlabeled subset of VoxPopuli corpus.
Note: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model.
Authors: Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux from Facebook AI
See the official website for more information, here
Please refer to this blog on how to fine-tune this model on a specific language. Note that you should replace "facebook/wav2vec2-large-xlsr-53" with this checkpoint for fine-tuning.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.