Model reference · open weights
distilhubert is an open-weight embedding model from ntu-spml. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | ntu-spml |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 23M |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 57k downloads / month |
| Licence | Open weights |
About
DistilHuBERT by NTU Speech Processing & Machine Learning Lab
The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.
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.
Paper: DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT
Authors: Heng-Jui Chang, Shu-wen Yang, Hung-yi Lee
Abstract Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success of these methods, they require large memory and high pre-training costs, making them inaccessible for researchers in academia and small companies. Therefore, this paper introduces DistilHuBERT, a novel multi-task learning framework to distill hidden representations from a HuBERT model directly. This method reduces HuBERT's size by 75% and 73% faster while retaining most performance in ten different tasks. Moreover, DistilHuBERT required little training time and data, opening the possibilities of pre-training personal and on-device SSL models for speech.
The original model can be found under https://github.com/s3prl/s3prl/tree/master/s3prl/upstream/distiller .
See this blog for more information on how to fine-tune the model. Note that the class Wav2Vec2ForCTC has to be replaced by HubertForCTC.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys distilhubert for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (distilhubert 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":"distilhubert","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.