Thaka Wins KSAA-2026 Arabic Speech Diacritization Task with Regularized Fine-Tuning of CATT-Whisper
The Thaka team describes their winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization, which requires producing fully diacritized Arabic text from speech audio and undiacritized transcripts. Their approach fine-tunes CATT-Whisper, a multimodal model combining a CATT text encoder with a frozen Whisper speech encoder, under severe data constraints (2,327 training samples, no external data). Key techniques include R-Drop consistency regularization, Optuna-optimized hyperparameters with high weight decay, Focal Loss, and Monte Carlo Dropout inference averaging over 200 stochastic forward passes across four checkpoints. The system achieves 23.26% WER on the primary metric, placing first among all participants.
Related guides (1)
Related events (8)
Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers
This Hugging Face blog post provides a practical guide for fine-tuning OpenAI's Whisper model for multilingual automatic speech recognition using the Transformers library. It covers dataset preparation, training configuration, and evaluation using the Word Error Rate metric. The post targets practitioners seeking to adapt Whisper to low-resource or domain-specific languages.
KIT submission to IWSLT 2026 cross-lingual voice cloning track with language tag prompting and RL fine-tuning
Researchers from KIT describe their system for the IWSLT 2026 Cross-Lingual Voice Cloning shared task, which aims to synthesize speech in a target language while preserving source-speaker identity. The system builds on FishAudio-S2-Pro, a multilingual TTS model, and introduces language tag prompting to reduce accent leakage, RL fine-tuning for intelligibility, and a reference-conditioned lexical matching method for domain-specific pronunciation. Language prompting yields the largest gains; lexical matching provides consistent improvements on matched subsets.
Introducing Whisper
OpenAI introduced Whisper, an open-source automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. The model demonstrates strong robustness to accents, background noise, and technical language, approaching human-level accuracy in English transcription. Whisper supports transcription in multiple languages as well as translation to English, and the weights and inference code were released publicly.
Speech-based dementia screening using Whisper embeddings to compensate for nonverbal subtest omissions
Researchers present a speech-based evaluation system for the German Syndrom-Kurz-Test dementia screening battery, combining transcript-derived scores with Whisper embeddings to reduce transcription scoring errors. The system also approximates expert overall ratings even when motor (nonverbal) subtests are omitted, addressing a key accessibility limitation of speech-only assessment. Models show strong correlation with expert ratings and effective discrimination between cognitive status groups.
Continual learning approach for disfluency-aware ASR with explicit disfluency tokens
A new arXiv preprint addresses the challenge of transcribing disfluent speech (hesitations, repetitions, fillers) in ASR systems, which typically omit such markers causing information loss. The authors introduce explicit disfluency tokens into a pretrained ASR model and apply continual learning to adapt across datasets with varying disfluency distributions while mitigating catastrophic forgetting. The work identifies a trade-off between disfluency marker learning and general ASR performance, and finds a consistent cross-attention head mechanism shared across continual learning methods.
AlignAtt4LLM adapts simultaneous speech translation policy to decoder-only LLMs for IWSLT 2026
Researchers present AlignAtt4LLM, a simultaneous speech translation system for IWSLT 2026 covering English to German, Italian, and Chinese. The system cascades Qwen3-ASR for incremental transcription with Gemma-4 E4B-it for translation, applying a novel AlignAtt policy adapted for decoder-only LLMs that lack encoder-decoder cross-attention. Key contributions include explicit source span prompting, offline alignment head selection, and query/key capture to recover a usable attention-based read/write policy. The system outperforms IWSLT 2026 baselines for European language pairs in both low- and high-latency regimes.
ADAS: Attention-Discounted Adaptive Sampler improves parallel decoding for masked diffusion language models
Researchers propose ADAS, a training-free reranking rule for masked diffusion language model decoding that addresses token interaction failures in parallel token commitment. The method greedily penalizes candidates that attend strongly to already-selected uncertain positions, using attention weights as soft marginal penalties rather than hard constraints. Evaluated on LLaDA-8B-Base and Dream-7B-Base across GSM8K, MATH500, HumanEval, and MBPP, ADAS improves low-NFE performance by 9–10 percentage points on average when plugged into existing samplers with only 3.1% runtime overhead.
Blazingly Fast Whisper Transcriptions with Inference Endpoints
Hugging Face published a blog post detailing optimized Whisper speech-to-text transcription deployments via their Inference Endpoints service. The post covers performance improvements using faster-whisper or similar optimized backends to achieve significantly reduced transcription latency. This is positioned as a practical deployment guide for production speech recognition workloads.