Casimiro Ferreira's picture

Casimiro Ferreira

Jarbas

·

https://tigregotico.pt

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

yuriyvnv/WAVe-1B-Multimodal-NL

reacted to yuriyvnv's post with 🔥 3 days ago

📄 The WAVe paper is officially out in the Information Sciences Journal. You saw the PT and NL model releases earlier this year. This is the peer-reviewed paper behind them, with the full method, ablations, and downstream ASR evaluation. Quick recap: WAVe is a 1B multimodal embedding model that filters synthetic speech at the word level, not the sentence level. On Portuguese ASR it cuts training steps by 34%, improves cross-domain generalization by 50%, and matches WER with 30% less synthetic data. 📦 Resources - Paper: https://www.sciencedirect.com/science/article/pii/S0020025526005220 - PT model: https://huggingface.co/yuriyvnv/WAVe-1B-Multimodal-PT - NL model: https://huggingface.co/yuriyvnv/WAVe-1B-Multimodal-NL - Collection: https://huggingface.co/collections/yuriyvnv/multi-modal-embeddings-for-synthetic-transcript-filtering - Code: https://github.com/yuriyvnv/WAVe If you train ASR on synthetic or back-translated data, would like to see WAVe benchmarked on other languages. @reach-vb @ylacombe @hf-audio @BramVanroy #speech #asr #multimodal #syntheticdata #lowresource

liked a dataset 3 days ago

apptek-com/apptek_callcenter_dialogues

View all activity

Organizations

New activity in OpenVoiceOS/proxectonos-celtia-vits-graphemes-onnx 9 months ago

Help . I don't seem to be able to use this model on Sherpa Onnx in Android

#1 opened 9 months ago by

New activity in fdemelo/xlm-roberta-ovos-intent-classifier 12 months ago

Create README.md

#1 opened 12 months ago by

New activity in projecte-aina/matxa-tts-cat-multiaccent over 1 year ago

Speaker ids - genders and accents

#2 opened over 1 year ago by