| Google speech_embedding/1 (TensorFlow1 / speech-embedding / version 1) |
| Original work published by Google under the Apache License, Version 2.0. |
| Source: https://www.kaggle.com/models/google/speech-embedding/TensorFlow1/speech-embedding/1 |
| Original archive SHA-256: |
| 0f626c42009c1eb916401b7b2800229a211e43100115bc591b9afbf1b60da27f |
|
|
| Paper: James Lin, Kevin Kilgour, Dominik Roblek, Matthew Sharifi, |
| "Training Keyword Spotters with Limited and Synthesized Speech Data", |
| arXiv:2002.01322. https://arxiv.org/abs/2002.01322 |
|
|
| This repository contains a PyTorch conversion made by Drew Bednar for naptrap. |
| It is not affiliated with or endorsed by Google. |
|
|
| Modifications to the original work: |
| - the TensorFlow graph was re-implemented with PyTorch operations; |
| - HWIO convolution kernels were transposed to OIHW; |
| - the original inference-time spatial-mean subtraction was applied to the |
| first convolution kernel ahead of time; |
| - the weights were stored in safetensors format. |
| All trained parameters, normalization statistics and frontend constants are |
| otherwise unchanged. No training or fine-tuning was performed. |
|
|
| The original archive contained no NOTICE file. |
|
|
