Trained Model for Deep Speech 2 for MLPerf Inference (Cloud)

Basic Information: Application: Speech To Text ML Task: Deep Speech 2 Framework: PyTorch v0.4.0 How to get: "wget https://zenodo.org/record/1713294/files/trained_model_deepspeech2.zip" Training Information: Quality: 21.1 WER (on test-clean set) Precision: single-precision float Is Quantized: no Is ONNX: no Dataset: LibriSpeech

This is the inference model for Deep Speech 2 on PyTorch. The model is trained using LibriSpeech 1000hr dataset (train-clean-100.tar.gz, train-clean-360.tar.gz, train-other-500.tar.gz) for 20 epochs.

Related Organizations

University of Toronto
Canada

Keywords

Deep Speech 2, Speech Recognition, Inference, LibriSpeech, PyTorch, Pretrained Model

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average