emiyasstar/ch-w2v-conformer-norelpos
The ch-w2v-conformer model uses following datasets to pretrain:
ISML datasets (6 languages,70k hours): internal dataset contains 40k hours Chinese, Cantonese, Tibetan, Inner Mongolian, Inner Kazakh, Uighur.
Babel datasets (17 languages, 2k hours): Assamese, Bengali, Cantonese, Cebuano, Georgian, Haitian, Kazakh, Kurmanji, Lao, Pashto, Swahili, Tagalog, Tamil, Tok, Turkish, Vietnamese, Zulu
After pretraining, we build ASR system based on CTC-Attention structure. In very low resource task, we find that if too many initialization network structures are constructed in the upper layer of pre-training conformer encoder, the migration performance of the pre-training model will be destroyed, so we only build a single-layer transformer decoder for joint training.
pretrained model link:
constrained-plus Task Performance
- Languages: Cantonese,mongolian,kazakh
- config: conf/trainconformerlarge_10h.yaml
- Feature info: using mfcc feature, with dither 1.0, without cmvn
- Training info: lr 0.001, batch size 10, 4 gpus on V100, acc_grad 1, 80 epochs
- Decoding info: ctcweight 0.5, averagenum 35
dev set results trained only with 10 hours training set