metadata
language:
- zh
license: apache-2.0
datasets:
- mozilla-foundation/common_voice_16_0
model-index:
- name: Wav2Vec2-BERT - Alvin
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_16_0 yue
type: mozilla-foundation/common_voice_16_0
config: yue
split: test
args: yue
metrics:
- name: Normalized CER
type: cer
value: 20.5
Wav2Vec2-BERT - Alvin
This model is a fine-tuned version of facebook/w2v-bert-2.0. This has a CER of 20.5
Training and evaluation data
For training, three datasets were used:
- Common Voice 16
zh-HK
andyue
Train Set - CantoMap: Winterstein, Grégoire, Tang, Carmen and Lai, Regine (2020) "CantoMap: a Hong Kong Cantonese MapTask Corpus", in Proceedings of The 12th Language Resources and Evaluation Conference, Marseille: European Language Resources Association, p. 2899-2906.
- Cantonse-ASR: Yu, Tiezheng, Frieske, Rita, Xu, Peng, Cahyawijaya, Samuel, Yiu, Cheuk Tung, Lovenia, Holy, Dai, Wenliang, Barezi, Elham, Chen, Qifeng, Ma, Xiaojuan, Shi, Bertram, Fung, Pascale (2022) "Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset", 2022. Link: https://arxiv.org/pdf/2201.02419.pdf
Code Example
from transformers import pipeline
bert_asr = pipeline(
"automatic-speech-recognition", model="alvanlii/wav2vec2-BERT-cantonese", device="cuda"
)
text = pipe(file)["text"]
Training Hyperparameters
- learning_rate: 1e-4
- train_batch_size: 4 (on 1 3090)
- eval_batch_size: 1
- gradient_accumulation_steps: 32
- total_train_batch_size: 32x4=128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_warmup_steps: 500
Training Results
Training Loss | Step | Validation Loss | CER |
---|---|---|---|
2.416 | 1200 | 1.615 | 0.4246 |
1.313 | 4200 | 0.9049 | 0.2745 |
1.090 | 7200 | 0.7463 | 0.2388 |
0.907 | 9600 | 0.6820 | 0.2172 |