diff options
| -rw-r--r-- | .gitignore | 2 | ||||
| -rw-r--r-- | data/.gitkeep | 0 | ||||
| -rw-r--r-- | license | 13 | ||||
| -rw-r--r-- | readme.md | 9 | ||||
| -rw-r--r-- | requirements.txt | 2 | ||||
| -rw-r--r-- | train.py | 11 |
6 files changed, 37 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..f45af34 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +venv/ +data/ diff --git a/data/.gitkeep b/data/.gitkeep new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/data/.gitkeep @@ -0,0 +1,13 @@ + DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE + Version 2, December 2004 + +Copyright (C) 2023 Marvin Borner <develop@marvinborner.de> + +Everyone is permitted to copy and distribute verbatim or modified +copies of this license document, and changing it is allowed as long +as the name is changed. + + DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. You just DO WHAT THE FUCK YOU WANT TO. diff --git a/readme.md b/readme.md new file mode 100644 index 0000000..c648cf6 --- /dev/null +++ b/readme.md @@ -0,0 +1,9 @@ +# CTC LSTM + +> spoken word recognition using CTC LSTMs + +## Installation + +- `python -m venv venv` +- `./venv/bin/pip install -r requirements.txt` +- `./venv/bin/python train.py` diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..c889304 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,2 @@ +torchaudio +numpy diff --git a/train.py b/train.py new file mode 100644 index 0000000..ebeb4d4 --- /dev/null +++ b/train.py @@ -0,0 +1,11 @@ +#!/bin/env python3 + +import torchaudio + +# download the datasets +train_dataset = torchaudio.datasets.LIBRISPEECH( + "./data", url="train-clean-100", download=True +) +test_dataset = torchaudio.datasets.LIBRISPEECH( + "./data", url="test-clean", download=True +) |