New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Streaming ASRモデルの学習 #10

Open

fujimotos opened this issue Feb 6, 2023 · 0 comments

Member

fujimotos commented Feb 6, 2023

このチケットのゴール

現在はConformer-Transformerモデルで推論を行っているが、時間長に対し2乗の計算量が必要になる。
このため、64GBのメモリを搭載したGPUでも一度に推論できるのは概ね数分である。
より長い音声に対応したモデルを検証し、より長い音声の推論をサポートする。

参考

ESPnet2 real streaming Transformer demonstration
https://espnet.github.io/espnet/notebook/espnet2_streaming_asr_demo.html
RNNベースのCSJ学習レシピ
https://github.com/espnet/espnet/blob/master/egs2/csj/asr1/conf/tuning/train_asr_rnn.yaml

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment