XLS-R is Facebook AI's large-scale multilingual pretrained model for speech (the "XLM-R for Speech"). It is pretrained on 436k hours of unlabeled speech, including VoxPopuli, MLS, CommonVoice, BABEL, and VoxLingua107. It uses the wav2vec 2.0 objective, in 128 languages. When using the model make sure that your speech input is sampled at 16kHz.
Note
: This model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Translation, or Classification. Check out
this blog
for more information about ASR.
Abstract
This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on 436K hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech recognition, XLS-R improves over the best known prior work on BABEL, MLS, CommonVoice as well as VoxPopuli, lowering error rates by 20%-33% relative on average. XLS-R also sets a new state of the art on VoxLingua107 language identification. Moreover, we show that with sufficient model size, cross-lingual pretraining can outperform English-only pretraining when translating English speech into other languages, a setting which favors monolingual pretraining. We hope XLS-R can help to improve speech processing tasks for many more languages of the world.
wav2vec2-xls-r-1b huggingface.co is an AI model on huggingface.co that provides wav2vec2-xls-r-1b's model effect (), which can be used instantly with this facebook wav2vec2-xls-r-1b model. huggingface.co supports a free trial of the wav2vec2-xls-r-1b model, and also provides paid use of the wav2vec2-xls-r-1b. Support call wav2vec2-xls-r-1b model through api, including Node.js, Python, http.
wav2vec2-xls-r-1b huggingface.co is an online trial and call api platform, which integrates wav2vec2-xls-r-1b's modeling effects, including api services, and provides a free online trial of wav2vec2-xls-r-1b, you can try wav2vec2-xls-r-1b online for free by clicking the link below.
facebook wav2vec2-xls-r-1b online free url in huggingface.co:
wav2vec2-xls-r-1b is an open source model from GitHub that offers a free installation service, and any user can find wav2vec2-xls-r-1b on GitHub to install. At the same time, huggingface.co provides the effect of wav2vec2-xls-r-1b install, users can directly use wav2vec2-xls-r-1b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.