bert-base-spanish-wwm-uncased

Model overview

bert-base-spanish-wwm-uncased is published by dccuchile as a BERT fill-mask model. The captured configuration identifies BertForMaskedLM with model type bert and Transformers support. According to the model card, it is the uncased BETO variant, a Spanish BERT model trained on a big Spanish corpus with Whole Word Masking.

Recorded capabilities

Use cases in the source record

• Spanish masked-language-modeling and fill-mask experiments using the publisher's documented uncased BETO checkpoint.
• Spanish NLP evaluations that revisit the card's comparison of BETO against multilingual BERT baselines.

Limitations and unknowns

• No parameter count was extracted from this record.
• No context-window value was extracted from this record.
• License is unresolved: structured metadata carries no license and the card's CC BY 4.0 statement is an uncertain intent disclaimer.
• Benchmark tables are referenced but no numeric scores were extracted; comparison claims reflect literature as of October 2019.
• Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: dccuchile/bert-base-spanish-wwm-uncased

Captured: Unknown. Processed: 2026-09-07T19:34:43.428916+00:00.

BETO: Spanish BERT BETO is a BERT model trained on a big Spanish corpus . BETO is of size similar to a BERT-Base and was trained with the Whole Word Masking technique. Below you find Tensorflow and Pytorch checkpoints for the uncased and cased versions, as well as some results for Spanish benchmarks comparing BETO with Multilingual BERT as well as other (not BERT-based) models. Download BETO uncased tensorflow_weights pytorch_weights vocab , config BETO cased tensorflow_weights pytorch_weights vocab , config All models use a vocabulary of about 31k BPE subwords constructed using SentencePiece and were trained for 2M steps. Benchmark…