Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

• URL: http://arxiv.org/abs/2311.00430v1
• Date: Wed, 1 Nov 2023 10:45:07 GMT
• Title: Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
• Authors: Sanchit Gandhi, Patrick von Platen, Alexander M. Rush
• Abstract summary: Distil-Whisper is designed to be paired with Whisper for speculative decoding, yielding a 2 times speed-up. Distil-Whisper is 5.8 times faster with 51% fewer parameters, while performing to within 1% WER on out-of-distribution test data. To facilitate further research in this domain, we make our training code, inference code and models publicly accessible.
• Score: 75.74809713084282
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale open-source dataset which we use to distill the Whisper model into a smaller variant, called Distil-Whisper. Using a simple word error rate (WER) heuristic, we select only the highest quality pseudo-labels for training. The distilled model is 5.8 times faster with 51% fewer parameters, while performing to within 1% WER on out-of-distribution test data in a zero-shot transfer setting. Distil-Whisper maintains the robustness of the Whisper model to difficult acoustic conditions, while being less prone to hallucination errors on long-form audio. Distil-Whisper is designed to be paired with Whisper for speculative decoding, yielding a 2 times speed-up while mathematically ensuring the same outputs as the original model. To facilitate further research in this domain, we make our training code, inference code and models publicly accessible.

Related papers

• Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model [0.0]
  OpenAI's Whisper Automated Speech Recognition model excels in generalizing across diverse datasets and domains. We propose a method to enhance transcription accuracy without explicit fine-tuning or altering model parameters.
  arXiv  Detail & Related papers  (2024-10-24T01:58:11Z)
• Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy [34.02350195269502]
  We formalize the problem of data pruning with re-labeling. We propose a novel data pruning algorithm, Prune4Rel, that finds a subset maximizing the total neighborhood confidence of all training examples.
  arXiv  Detail & Related papers  (2023-11-02T05:40:26Z)
• Multi-scale Diffusion Denoised Smoothing [79.95360025953931]
  randomized smoothing has become one of a few tangible approaches that offers adversarial robustness to models at scale. We present scalable methods to address the current trade-off between certified robustness and accuracy in denoised smoothing. Our experiments show that the proposed multi-scale smoothing scheme combined with diffusion fine-tuning enables strong certified robustness available with high noise level.
  arXiv  Detail & Related papers  (2023-10-25T17:11:21Z)
• Combating Label Noise With A General Surrogate Model For Sample Selection [84.61367781175984]
  We propose to leverage the vision-language surrogate model CLIP to filter noisy samples automatically. We validate the effectiveness of our proposed method on both real-world and synthetic noisy datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:43:27Z)
• Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion [85.54515118077825]
  This paper proposes a linear diffusion model (LinDiff) based on an ordinary differential equation to simultaneously reach fast inference and high sample quality. To reduce computational complexity, LinDiff employs a patch-based processing approach that partitions the input signal into small patches. Our model can synthesize speech of a quality comparable to that of autoregressive models with faster synthesis speed.
  arXiv  Detail & Related papers  (2023-06-09T07:02:43Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech [63.780196620966905]
  We propose ProDiff, on progressive fast diffusion model for high-quality text-to-speech. ProDiff parameterizes the denoising model by directly predicting clean data to avoid distinct quality degradation in accelerating sampling. Our evaluation demonstrates that ProDiff needs only 2 iterations to synthesize high-fidelity mel-spectrograms. ProDiff enables a sampling speed of 24x faster than real-time on a single NVIDIA 2080Ti GPU.
  arXiv  Detail & Related papers  (2022-07-13T17:45:43Z)
• Language Models in the Loop: Incorporating Prompting into Weak Supervision [11.10422546502386]
  We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Instead of applying the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for labeling functions in a weak supervision framework.
  arXiv  Detail & Related papers  (2022-05-04T20:42:40Z)
• Learning from Noisy Labels for Entity-Centric Information Extraction [17.50856935207308]
  We propose a simple co-regularization framework for entity-centric information extraction. These models are jointly optimized with task-specific loss, and are regularized to generate similar predictions. In the end, we can take any of the trained models for inference.
  arXiv  Detail & Related papers  (2021-04-17T22:49:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.