End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: openai/whisper-tiny
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- common_voice_11_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: whisper-tiny-fi-lora
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# whisper-tiny-fi-lora
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_11_0 dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.6958
|
| 23 |
+
- Wer: 75.1203
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- training_steps: 5000
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
| 56 |
+
| 3.7258 | 0.3690 | 100 | 3.6261 | 82.2153 |
|
| 57 |
+
| 2.1228 | 0.7380 | 200 | 1.9384 | 86.0270 |
|
| 58 |
+
| 0.951 | 1.1070 | 300 | 0.9630 | 82.1964 |
|
| 59 |
+
| 0.7932 | 1.4760 | 400 | 0.8430 | 82.5644 |
|
| 60 |
+
| 0.7635 | 1.8450 | 500 | 0.8000 | 85.1967 |
|
| 61 |
+
| 0.7242 | 2.2140 | 600 | 0.7735 | 79.3094 |
|
| 62 |
+
| 0.7099 | 2.5830 | 700 | 0.7573 | 82.7437 |
|
| 63 |
+
| 0.6686 | 2.9520 | 800 | 0.7504 | 80.5265 |
|
| 64 |
+
| 0.6476 | 3.3210 | 900 | 0.7415 | 78.7716 |
|
| 65 |
+
| 0.6494 | 3.6900 | 1000 | 0.7316 | 83.7626 |
|
| 66 |
+
| 0.6069 | 4.0590 | 1100 | 0.7307 | 78.5263 |
|
| 67 |
+
| 0.6463 | 4.4280 | 1200 | 0.7254 | 79.0358 |
|
| 68 |
+
| 0.5897 | 4.7970 | 1300 | 0.7210 | 78.9414 |
|
| 69 |
+
| 0.5816 | 5.1661 | 1400 | 0.7161 | 79.0924 |
|
| 70 |
+
| 0.5677 | 5.5351 | 1500 | 0.7174 | 76.4978 |
|
| 71 |
+
| 0.5584 | 5.9041 | 1600 | 0.7116 | 77.7715 |
|
| 72 |
+
| 0.5027 | 6.2731 | 1700 | 0.7081 | 76.0921 |
|
| 73 |
+
| 0.5214 | 6.6421 | 1800 | 0.7114 | 76.3657 |
|
| 74 |
+
| 0.5503 | 7.0111 | 1900 | 0.7113 | 76.3751 |
|
| 75 |
+
| 0.5057 | 7.3801 | 2000 | 0.7065 | 75.7713 |
|
| 76 |
+
| 0.5338 | 7.7491 | 2100 | 0.7052 | 76.4978 |
|
| 77 |
+
| 0.4457 | 8.1181 | 2200 | 0.7052 | 75.8562 |
|
| 78 |
+
| 0.5183 | 8.4871 | 2300 | 0.7017 | 76.7337 |
|
| 79 |
+
| 0.4988 | 8.8561 | 2400 | 0.7006 | 75.9600 |
|
| 80 |
+
| 0.4858 | 9.2251 | 2500 | 0.7001 | 75.6958 |
|
| 81 |
+
| 0.5024 | 9.5941 | 2600 | 0.7009 | 76.8752 |
|
| 82 |
+
| 0.5111 | 9.9631 | 2700 | 0.6998 | 75.6015 |
|
| 83 |
+
| 0.4985 | 10.3321 | 2800 | 0.6987 | 77.9791 |
|
| 84 |
+
| 0.4725 | 10.7011 | 2900 | 0.6975 | 77.4035 |
|
| 85 |
+
| 0.4497 | 11.0701 | 3000 | 0.6970 | 75.3090 |
|
| 86 |
+
| 0.4534 | 11.4391 | 3100 | 0.6972 | 75.4883 |
|
| 87 |
+
| 0.4839 | 11.8081 | 3200 | 0.6962 | 78.0262 |
|
| 88 |
+
| 0.4543 | 12.1771 | 3300 | 0.6970 | 75.7147 |
|
| 89 |
+
| 0.4586 | 12.5461 | 3400 | 0.6978 | 75.6581 |
|
| 90 |
+
| 0.4656 | 12.9151 | 3500 | 0.6997 | 76.3374 |
|
| 91 |
+
| 0.4177 | 13.2841 | 3600 | 0.6951 | 76.0449 |
|
| 92 |
+
| 0.4443 | 13.6531 | 3700 | 0.6965 | 75.3279 |
|
| 93 |
+
| 0.4698 | 14.0221 | 3800 | 0.6975 | 75.3562 |
|
| 94 |
+
| 0.4412 | 14.3911 | 3900 | 0.6957 | 75.2807 |
|
| 95 |
+
| 0.4027 | 14.7601 | 4000 | 0.6955 | 77.0356 |
|
| 96 |
+
| 0.4755 | 15.1292 | 4100 | 0.6963 | 75.4505 |
|
| 97 |
+
| 0.4487 | 15.4982 | 4200 | 0.6950 | 75.1014 |
|
| 98 |
+
| 0.4237 | 15.8672 | 4300 | 0.6967 | 75.2241 |
|
| 99 |
+
| 0.4222 | 16.2362 | 4400 | 0.6975 | 75.3090 |
|
| 100 |
+
| 0.408 | 16.6052 | 4500 | 0.6975 | 75.2618 |
|
| 101 |
+
| 0.4671 | 16.9742 | 4600 | 0.6947 | 75.0448 |
|
| 102 |
+
| 0.448 | 17.3432 | 4700 | 0.6954 | 75.2901 |
|
| 103 |
+
| 0.4253 | 17.7122 | 4800 | 0.6956 | 75.0826 |
|
| 104 |
+
| 0.44 | 18.0812 | 4900 | 0.6959 | 75.1392 |
|
| 105 |
+
| 0.4053 | 18.4502 | 5000 | 0.6958 | 75.1203 |
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
### Framework versions
|
| 109 |
+
|
| 110 |
+
- Transformers 4.42.3
|
| 111 |
+
- Pytorch 2.1.2
|
| 112 |
+
- Datasets 2.20.0
|
| 113 |
+
- Tokenizers 0.19.1
|