Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

• URL: http://arxiv.org/abs/2501.03643v2
• Date: Sat, 11 Jan 2025 06:24:11 GMT
• Title: Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
• Authors: Haoning Xu, Zhaoqing Li, Zengrui Jin, Huimeng Wang, Youjun Chen, Guinan Li, Mengzhe Geng, Shujie Hu, Jiajun Deng, Xunying Liu,
• Abstract summary: This paper presents a novel mixed-precision quantization approach for speech foundation models.<n>Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models.
• Score: 32.529198141470395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quantization in separate and disjointed stages, while incurring no statistically word error rate (WER) increase over the 32-bit full-precision models. The system compression time of wav2vec2.0-base and HuBERT-large models is reduced by up to 1.9 and 1.5 times over the two-stage mixed-precision baselines, while both produce lower WERs. The best-performing 3.5-bit mixed-precision quantized HuBERT-large model produces a lossless compression ratio of 8.6x over the 32-bit full-precision system.

Related papers

• Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [41.299675080384]
  Mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression.
  arXiv  Detail & Related papers  (2024-01-03T05:26:57Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Hyperspherical Quantization: Toward Smaller and More Accurate Models [17.154801913113566]
  Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings. Binary and other low-precision quantization methods can reduce the model size up to 32$times$, however, at the cost of a considerable accuracy drop. We propose an efficient framework for ternary quantization to produce smaller and more accurate compressed models.
  arXiv  Detail & Related papers  (2022-12-24T04:42:15Z)
• Online Model Compression for Federated Learning with Large Models [8.48327410170884]
  Online Model Compression (OMC) is a framework that stores model parameters in a compressed format and decompresses them only when needed. OMC can reduce memory usage and communication cost of model parameters by up to 59% while attaining comparable accuracy and training speed when compared with full-precision training.
  arXiv  Detail & Related papers  (2022-05-06T22:43:03Z)
• Compression of Generative Pre-trained Language Models via Quantization [62.80110048377957]
  We find that previous quantization methods fail on generative tasks due to the textithomogeneous word embeddings We propose a token-level contrastive distillation to learn distinguishable word embeddings, and a module-wise dynamic scaling to make quantizers adaptive to different modules.
  arXiv  Detail & Related papers  (2022-03-21T02:11:35Z)
• On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency [47.90235939359225]
  We propose a novel mixup strategy for pre-trained language models that improves model calibration further. Our method achieves the lowest expected calibration error compared to strong baselines on both in-domain and out-of-domain test samples.
  arXiv  Detail & Related papers  (2022-03-14T23:45:08Z)
• Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time [69.7693300927423]
  We show that averaging the weights of multiple models fine-tuned with different hyper parameter configurations improves accuracy and robustness. We show that the model soup approach extends to multiple image classification and natural language processing tasks.
  arXiv  Detail & Related papers  (2022-03-10T17:03:49Z)
• Automatic Mixed-Precision Quantization Search of BERT [62.65905462141319]
  Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. These models usually contain millions of parameters, which prevents them from practical deployment on resource-constrained devices. We propose an automatic mixed-precision quantization framework designed for BERT that can simultaneously conduct quantization and pruning in a subgroup-wise level.
  arXiv  Detail & Related papers  (2021-12-30T06:32:47Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)
• High correlated variables creator machine: Prediction of the compressive strength of concrete [0.0]
  We introduce a novel hybrid model for predicting the compressive strength of concrete using ultrasonic pulse velocity (UPV) and rebound number (RN) High correlated variables creator machine (HVCM) is used to create the new variables that have a better correlation with the output and improve the prediction models. The results show that HCVCM-ANFIS can predict the compressive strength of concrete better than all other models.
  arXiv  Detail & Related papers  (2020-09-11T15:06:05Z)
• Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
  We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator. In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
  arXiv  Detail & Related papers  (2020-04-15T20:10:53Z)

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.