Instructions to use seastar105/whisper-base-kspon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seastar105/whisper-base-kspon with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="seastar105/whisper-base-kspon")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("seastar105/whisper-base-kspon") model = AutoModelForSpeechSeq2Seq.from_pretrained("seastar105/whisper-base-kspon", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model Description
OpenAIμ whisper-base λͺ¨λΈμ μλ λ°μ΄ν°μ μΌλ‘ νμ΅ν λͺ¨λΈμ λλ€.
- νκ΅μ΄ μμ± (https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=123)
train_steps: 5000
warmup_steps: 500
lr scheduler: linear warmup cosine decay
max learning rate: 1e-4
batch size: 128
max_grad_norm: 1.0
adamw_beta1: 0.9
adamw_beta2: 0.98
Evaluation
https://github.com/rtzr/Awesome-Korean-Speech-Recognition
μ λ ν¬μ§ν 리μμ μ£Όμ μμλ³ νμ μμ±μ μ μΈν ν μ€νΈμ κ²°κ³Όμ λλ€. μλ ν μ΄λΈμμ whisper_base_ksponμ΄ λ³Έ λͺ¨λΈ μ±λ₯μ λλ€.
+--------------------------+----------+-----------+---------------+------------+---------------+--------------+-------------+-------------+
| Model | cv_15_ko | fleurs_ko | kcall_testset | kconf_test | kcounsel_test | klec_testset | kspon_clean | kspon_other |
+--------------------------+----------+-----------+---------------+------------+---------------+--------------+-------------+-------------+
| whisper_base | 21.16 | 11.89 | 42.56 | 27.62 | 22.24 | 28.65 | 30.41 | 27.02 |
| whisper_base_kspon | 26.63 | 13.95 | 42.05 | 29.61 | 26.21 | 28.72 | 12.58 | 13.48 |
| whisper_base_komix | 15.42 | 7.16 | 20.86 | 14.24 | 12.64 | 13.44 | 12.26 | 12.12 |
| whisper_turbo | 5.38 | 3.95 | 5.89 | 9.77 | 4.21 | 9.27 | 16.49 | 13.54 |
+--------------------------+----------+-----------+---------------+------------+---------------+--------------+-------------+-------------+
- Downloads last month
- 11