Downloads · 30 days
0
icefall_asr_yesno_tdnn
csukuangfj/icefall_asr_yesno_tdnn
icefall_asr_yesno_tdnn is a machine learning model from csukuangfj. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Refer to <https://github.com/k2-fsa/icefall/tree/master/egs/yesno/ASR for more information about this pre-trained model.
Access
Public
Updated Sep 22, 2021
Repo size
70.3 KB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.wav3 MB · 98%
At a glance
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 22, 2021
- SHA
- e2087b29
Model card
From the Hugging Face model README
Pre-trained TDNN models for the yesno dataset with icefall.
Refer to https://github.com/k2-fsa/icefall/tree/master/egs/yesno/ASR for more information about this pre-trained model.
You can find usage instructions there.
Sound files for testing the pre-trained model
The folder test_waves contains test sound files. They
are downloaded from https://www.openslr.org/1/.
There are 60 files in the dataset, 30 are used for training.
The remaining 30 files, contained in test_waves are kept for testing.
The code for splitting the dataset can be found at https://github.com/lhotse-speech/lhotse/blob/master/lhotse/recipes/yesno.py#L138
wave_files = list(corpus_dir.glob("*.wav"))
assert len(wave_files) == 60
wave_files.sort()
train_set = wave_files[::2]
test_set = wave_files[1::2]
assert len(train_set) == 30
assert len(test_set) == 30
- Created
- Mar 2, 2022
- Updated
- Sep 22, 2021