metadata
license: cc-by-sa-4.0
language:
- th
metrics:
- cer
- wer
library_name: espnet
pipeline_tag: automatic-speech-recognition
Model Card for Model ID
This is the baseline model of Thai-central in Thai-dialect corpus.
The training recipe was based on wsj recipe in espnet.
Model Description
This model is Hybrid CTC/Attention model with pre-trained HuBERT as the encoder.
This model trained on Thai-central for being the supervised pre-trained model in transfer-based curriculum learning experiment.
you can demo on colab with this link. (Free google colab cannot inferences > 3 seconds of speech.)
Evaluation
For evaluation, the metrics are CER and WER. before WER evaluation, transcriptions were re-tokenized using newmm tokenizer in PyThaiNLP
In this reposirity, we also provide the vocabulary for building the newmm tokenizer using this script:
from pythainlp import word_tokenize
tokenized_sentence_list = word_tokenize(<your_sentence>)
CER = 2.0
WER = 6.9
Paper
@inproceedings{suwanbandit23_interspeech,
author={Artit Suwanbandit and Burin Naowarat and Orathai Sangpetch and Ekapol Chuangsuwanich},
title={{Thai Dialect Corpus and Transfer-based Curriculum Learning Investigation for Dialect Automatic Speech Recognition}},
year=2023,
booktitle={Proc. INTERSPEECH 2023},
pages={4069--4073},
doi={10.21437/Interspeech.2023-1828}
}