Model Detail
whisper-small
—whisper-small is an audio model with 121M parameters released by OpenAI. The model is registered under the automatic-speech-recognition pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
whisper-small ships with 121M parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
whisper-small is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Quantizing Whisper-small: How design choices affect ASR performance
arXiv:2511.08093v2 Announce Type: replace-cross Abstract: Large speech recognition models like Whisper-small achieve high accuracy but are difficult to deploy on edge devices due to their high computational demand. To this end, we present a unified, cross-library evaluation of post-training quantiza
Understanding Personalization Gains in Whisper
arXiv:2610.17019v1 Announce Type: new Abstract: Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across datasets, recording conditions, and metadata-based groups. We study when lightweight low-rank adaptation (LoRA) improves Whispe
Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR
arXiv:2610.09934v1 Announce Type: new Abstract: We describe the Itgan systems for the three ASR subtasks of NADI 2026, namely robust country-level ASR (1.1), mixed-dialect ASR (1.2), and Tunisian code-switched ASR (1.3). All three share one recipe, Whisper adapted with LoRA on consumer GPUs, and eac
Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
arXiv:2609.28739v1 Announce Type: new Abstract: Automatic speech recognition models are audited for demographic fairness at full precision, yet the models that ship to production have been quantized, pruned, and distilled. We ask whether post-training weight compression, which alters model weights r
BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech
arXiv:2609.29371v1 Announce Type: new Abstract: This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it. The corpus holds 35,374 samples of 3 to 15 s of podcast speech, labelled for turn state by combining speaker diarization with
Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
arXiv:2609.27980v1 Announce Type: new Abstract: Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the {\tt whisper-large-v3-turbo} variant reduced the dec
