This repository has been archived on 2026-03-23. You can view files and clone it, but cannot push or open issues or pull requests.
Fangjun Kuang 968e4a6609 Fix an error.
Nbest.fsa should always have token IDs as labels and
word IDs as aux_labels.
2021-09-13 20:55:26 +08:00
2021-09-13 20:55:26 +08:00
2021-07-24 17:13:20 +08:00
2021-07-15 17:36:48 +08:00
2021-07-15 17:36:48 +08:00
2021-07-15 19:52:01 +08:00
2021-08-24 21:30:30 +08:00

Installation

Please refer to https://icefall.readthedocs.io/en/latest/installation/index.html for installation.

Recipes

Please refer to https://icefall.readthedocs.io/en/latest/recipes/index.html for more information.

We provide two recipes at present:

yesno

This is the simplest ASR recipe in icefall and can be run on CPU. Training takes less than 30 seconds and gives you the following WER:

[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]

We do provide a Colab notebook for this recipe.

Open In Colab

LibriSpeech

We provide two models for this recipe: conformer CTC model and TDNN LSTM CTC model.

Conformer CTC Model

The best WER we currently have is:

test-clean test-other
WER 2.57% 5.94%

We provide a Colab notebook to run a pre-trained conformer CTC model: Open In Colab

TDNN LSTM CTC Model

The WER for this model is:

test-clean test-other
WER 6.59% 17.69%

We provide a Colab notebook to run a pre-trained TDNN LSTM CTC model: Open In Colab

Description
No description provided
Readme Apache-2.0 56 MiB
Languages
Python 97.9%
Shell 1.9%
Dockerfile 0.2%