Hugging Face's logo
Yuriy Perezhohin's picture
Open to Collab
11 4 24

Yuriy Perezhohin PRO

yuriyvnv
tahamajs's profile picture hectorAJM's profile picture John6666's profile picture
·
https://scholar.google.com/citations?user=I5uzFtwAAAAJ&hl=en

AI & ML interests

Automatic Speech Recognition, Embeddings, Code Generation, Synthetic Data Generation and Filtering

Recent Activity

updated a model about 9 hours ago
yuriyvnv/3layers_wt_alignment_PT_100_epochs
published a model about 9 hours ago
yuriyvnv/3layers_wt_alignment_PT_100_epochs
replied to their post 2 days ago
🎯 WAVe: 1B Multimodal Embedding Model for Word-Level Speech Quality Multimodal embeddings for speech + transcript that verify quality at the word level, not just sentence level. Catches mispronunciations, timing errors, and prosody issues that sentence-level filters miss. 📊 Impact on Portuguese ASR: • 34% reduction in training steps • 50% better cross-domain generalization • 30% less synthetic data needed • Word-aligned attention finds errors other methods miss 🏗️ Architecture: • Text: XLM-RoBERTa (278M params) • Audio: Wav2Vec2-BERT 2.0 (581M params) • Word Alignment: Multi-head attention + GLU (14M params) • Total: 1B parameters ``` from transformers import AutoModel, AutoProcessor processor = AutoProcessor.from_pretrained( "yuriyvnv/WAVe-1B-Multimodal-PT", trust_remote_code=True ) model = AutoModel.from_pretrained( "yuriyvnv/WAVe-1B-Multimodal-PT", trust_remote_code=True ) ``` # Assess speech-transcript alignment ``` inputs = processor(text="Olá, como está?", audio=audio_array, sampling_rate=16000, return_tensors="pt") quality = model(**inputs).quality_score.item() ``` Perfect for filtering synthetic speech datasets before ASR training. Model: https://huggingface.co/yuriyvnv/WAVe-1B-Multimodal-PT Code to create WAVe : https://github.com/yuriyvnv/WAVe #multimodal #speech #embeddings #asr #syntheticdata #qualityassessment
View all activity

Organizations

Remynd's profile picture