whisper-small-ko
ν΄λΉ λͺ¨λΈμ Whisper Smallμ μλμ AI hub datasetμ λν΄ νμΈνλμ μ§ννμ΅λλ€.
λ°μ΄ν°μ
μ ν¬κΈ°κ° ν° κ΄κ³λ‘ λ°μ΄ν°μ
μ λλ€νκ² μμ ν 5κ°λ‘ λλμ΄ νμ΅μ μ§ννμ΅λλ€.
Training results
Dataset | Training Loss | Epoch | Validation Loss | Wer |
---|---|---|---|---|
Dataset part1 | 0.1943 | 0.2 | 0.0853 | 9.48 |
dataset
ν΄λΉ λͺ¨λΈμ AI hubμ λ§μ λ°μ΄ν°μ
μ νλ²μ νμ΅μν¨ κ²μ΄ νΉμ§μ
λλ€.
ASRμ domainμ λν μμ‘΄λκ° λ§€μ° ν½λλ€. μ΄ λλ¬Έμ νλμ λ°μ΄ν°μ
μ νμ΅μ μν€λλΌλ λ€λ₯Έ λ°μ΄ν°μ
μ λν΄μ ν
μ€νΈλ₯Ό μ§ννλ©΄ μ±λ₯μ΄ ν¬κ² λ¨μ΄μ§κ² λ©λλ€.
μ΄λ° λΆλΆμ λ§κΈ° μν΄ μ΅λν λ§μ λ°μ΄ν°μ
μ ν λ²μ νμ΅μμΌ°μ΅λλ€.
μΆν μ¬ν¬λ¦¬λ μ΄λ¦°μμ΄, λ
ΈμΈμ μμ±μ adapterλ₯Ό νμ©νλ©΄ μ’μ μ±λ₯μ μ»μ μ μμ κ²μ
λλ€.
λ°μ΄ν°μ μ΄λ¦ | λ°μ΄ν° μν μ(train/test) |
---|---|
κ³ κ°μλμμ± | 2067668/21092 |
νκ΅μ΄ μμ± | 620000/3000 |
νκ΅μΈ λν μμ± | 2483570/142399 |
μμ λνμμ±(μΌλ°λ¨λ ) | 1886882/263371 |
λ³΅μ§ λΆμΌ μ½μΌν° μλ΄λ°μ΄ν° | 1096704/206470 |
μ°¨λλ΄ λν λ°μ΄ν° | 2624132/332787 |
λͺ λ Ήμ΄ μμ±(λ ΈμΈλ¨μ¬) | 137467/237469 |
μ 체 | 10916423(13946μκ°)/1206588(1474μκ°) |
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- gradient_accumulation_steps: 2
- warmup_ratio: 0.01,
- num_train_epoch: 1
- Downloads last month
- 755