We propose a novel one-pass multiple ASR systems joint compression and
quantization approach using an all-in-one neural model. A single compression
cycle allows multiple nested systems with varying Encoder depths, widths, and
quantization precision settings to be simultaneously constructed without the
need to train and store individual target systems separately. Experiments
consistently demonstrate the multiple ASR systems compressed in a single
all-in-one model produced a word error rate (WER) comparable to, or lower by up
to 1.01\% absolute (6.98\% relative) than individually trained systems of equal
complexity. A 3.4x overall system compression and training time speed-up was
achieved. Maximum model size compression ratios of 12.8x and 3.93x were
obtained over the baseline Switchboard-300hr Conformer and LibriSpeech-100hr
fine-tuned wav2vec2.0 models, respectively, incurring no statistically
significant WER increase.

我们提出了一种新颖的一次性多个 ASR 系统联合压缩和量化方法，使用一个全能模型。一个单独的压缩周期允许同时构建具有不同编码器深度、宽度和量化精度设置的多个嵌套系统，而无需单独训练和存储个别目标系统。实验证明，与等复杂度的单独训练系统相比，一个全能模型中压缩的多个 ASR 系统的字错误率（WER）相当，或更低至 1.01％绝对值（6.98％相对值）。整体系统压缩和训练时间加速了 3.4 倍。在基线 Switchboard-300hr Conformer 和 LibriSpeech-100hr fine-tuned wav2vec2.0 模型上，最大模型大小压缩比分别达到了 12.8 倍和 3.93 倍，没有引起统计上显著的 WER 增加。