Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-xls-r-300m_phone-mfa_korean – AI Model by slplab | AlphaNeural AI
You can deploy this model and start earning money today!
slplab
/
wav2vec2-xls-r-300m_phone-mfa_korean
like
0
transformers
pytorch
wav2vec2
automatic-speech-recognition
generated_from_trainer
ko
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
wav2vec2-xls-r-300m_phoneme-mfa_korean
This model is a fine-tuned version of
facebook/wav2vec2-xls-r-300m
on a phonetically balanced native Korean read-speech corpus.
Model Management by:
excalibur12
Training and Evaluation Data
Training Data
Data Name: Phonetically Balanced Native Korean Read-speech Corpus
Num. of Samples: 54,000 (540 speakers)
Audio Length: 108 Hours
Evaluation Data
Data Name: Phonetically Balanced Native Korean Read-speech Corpus
Num. of Samples: 6,000 (60 speakers)
Audio Length: 12 Hours
Training Hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 20 (EarlyStopping: patience: 5 epochs max)
mixed_precision_training: Native AMP
Evaluation Results
Phone Error Rate 3.88%
Monophthong-wise Error Rates: (To be posted)
Output Examples
output_examples
MFA-IPA Phoneset Tables
Vowels
mfa_ipa_chart_vowels
Consonants
mfa_ipa_chart_consonants
Experimental Results
Official implementation of the paper (
ICPhS 2023
)
Major error patterns of L2 Korean speech from five different L1s: Chinese (ZH), Vietnamese (VI), Japanese (JP), Thai (TH), English (EN)
Experimental Results
Framework versions
Transformers 4.21.3
Pytorch 1.12.1
Datasets 2.4.0
Tokenizers 0.12.1
