mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-13 12:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Colab notebook for the yesno dataset.

Browse Source
This commit is contained in:
Fangjun Kuang 2021-08-22 23:39:43 +08:00
parent 09587d1108
commit 88166c598b
5 changed files with 36 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@ -48,10 +48,22 @@ python3 -c "import icefall; print(icefall.__file__)"
It should print the path to `icefall`.
## Run recipes
## Recipes
At present, only LibriSpeech recipe is provided. Please
follow [egs/librispeech/ASR/README.md][LibriSpeech] to run it.
At present, two recipes are provided:
- [LibriSpeech][LibriSpeech]
- [yesno][yesno] [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1tIjjzaJc3IvGyKiMCDWO-TSnBgkcuN3B?usp=sharing)
### Yesno
For the yesno recipe, training with 50 epochs takes less than 2 minutes using **CPU**.
The WER is
```
[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]
```
## Use Pre-trained models
@ -60,6 +72,7 @@ for how to use pre-trained models.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1huyupXAcHsUrKaWfI83iMEJ6J0Nh0213?usp=sharing)
[yesno]: egs/yesno/ASR/README.md
[LibriSpeech]: egs/librispeech/ASR/README.md
[k2-install]: https://k2.readthedocs.io/en/latest/installation/index.html#
[k2]: https://github.com/k2-fsa/k2

5
egs/librispeech/ASR/local/compute_fbank_librispeech.py
View File

@ -2,7 +2,7 @@
"""
This file computes fbank features of the LibriSpeech dataset.
Its looks for manifests in the directory data/manifests.
It looks for manifests in the directory data/manifests.
The generated fbank features are saved in data/fbank.
"""
@ -53,7 +53,8 @@ def compute_fbank_librispeech():
continue
logging.info(f"Processing {partition}")
cut_set = CutSet.from_manifests(
recordings=m["recordings"], supervisions=m["supervisions"],
recordings=m["recordings"],
supervisions=m["supervisions"],
)
if "train" in partition:
cut_set = (

2
egs/librispeech/ASR/local/compute_fbank_musan.py
View File

@ -2,7 +2,7 @@
"""
This file computes fbank features of the musan dataset.
Its looks for manifests in the directory data/manifests.
It looks for manifests in the directory data/manifests.
The generated fbank features are saved in data/fbank.
"""

15
egs/yesno/ASR/README.md Normal file
View File

@ -0,0 +1,15 @@
## Yesno recipe
You can run the recipe with **CPU**.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1tIjjzaJc3IvGyKiMCDWO-TSnBgkcuN3B?usp=sharing)
The above Colab notebook finishes the training using **CPU**
within two minutes (50 epochs in total).
The WER is
```
[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]
```

2
egs/yesno/ASR/local/compute_fbank_yesno.py
View File

@ -2,7 +2,7 @@
"""
This file computes fbank features of the yesno dataset.
Its looks for manifests in the directory data/manifests.
It looks for manifests in the directory data/manifests.
The generated fbank features are saved in data/fbank.
"""