Commit
·
a438d8e
1
Parent(s):
3c63f4e
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: hindi_beekeeping_wav2vec2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# hindi_beekeeping_wav2vec2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6793
|
| 21 |
+
- Wer: 0.4048
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0003
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 5
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 26.5108 | 0.11 | 25 | 2.9146 | 1.1520 |
|
| 56 |
+
| 3.8351 | 0.22 | 50 | 2.1736 | 0.6667 |
|
| 57 |
+
| 2.1489 | 0.33 | 75 | 1.5539 | 0.5914 |
|
| 58 |
+
| 3.2097 | 0.44 | 100 | 1.9828 | 0.6840 |
|
| 59 |
+
| 1.5213 | 0.54 | 125 | 1.4369 | 0.5410 |
|
| 60 |
+
| 2.1797 | 0.65 | 150 | 1.7904 | 0.7449 |
|
| 61 |
+
| 1.2368 | 0.76 | 175 | 1.3543 | 0.5583 |
|
| 62 |
+
| 1.5755 | 0.87 | 200 | 1.5444 | 0.6712 |
|
| 63 |
+
| 1.1638 | 0.98 | 225 | 1.4639 | 0.6005 |
|
| 64 |
+
| 0.8985 | 1.09 | 250 | 1.0658 | 0.5139 |
|
| 65 |
+
| 0.9406 | 1.2 | 275 | 1.3181 | 0.5756 |
|
| 66 |
+
| 1.1215 | 1.31 | 300 | 1.0163 | 0.4680 |
|
| 67 |
+
| 1.3881 | 1.42 | 325 | 1.1547 | 0.5854 |
|
| 68 |
+
| 0.8113 | 1.53 | 350 | 0.9433 | 0.4771 |
|
| 69 |
+
| 0.689 | 1.63 | 375 | 1.0819 | 0.5064 |
|
| 70 |
+
| 0.726 | 1.74 | 400 | 1.0025 | 0.5252 |
|
| 71 |
+
| 0.6475 | 1.85 | 425 | 1.0670 | 0.5154 |
|
| 72 |
+
| 1.0345 | 1.96 | 450 | 0.9535 | 0.5019 |
|
| 73 |
+
| 0.8327 | 2.07 | 475 | 0.8866 | 0.4733 |
|
| 74 |
+
| 0.4843 | 2.18 | 500 | 0.9580 | 0.5087 |
|
| 75 |
+
| 0.6657 | 2.29 | 525 | 0.9019 | 0.4710 |
|
| 76 |
+
| 0.4843 | 2.4 | 550 | 0.8207 | 0.4665 |
|
| 77 |
+
| 0.6666 | 2.51 | 575 | 0.7377 | 0.4695 |
|
| 78 |
+
| 0.5012 | 2.61 | 600 | 0.8135 | 0.4537 |
|
| 79 |
+
| 0.7776 | 2.72 | 625 | 0.8131 | 0.4612 |
|
| 80 |
+
| 0.4538 | 2.83 | 650 | 0.8194 | 0.4590 |
|
| 81 |
+
| 0.5659 | 2.94 | 675 | 0.8480 | 0.4582 |
|
| 82 |
+
| 0.9362 | 3.05 | 700 | 0.8532 | 0.4485 |
|
| 83 |
+
| 0.3629 | 3.16 | 725 | 0.8447 | 0.4582 |
|
| 84 |
+
| 0.5201 | 3.27 | 750 | 0.7486 | 0.4409 |
|
| 85 |
+
| 0.3513 | 3.38 | 775 | 0.7865 | 0.4439 |
|
| 86 |
+
| 0.4152 | 3.49 | 800 | 0.7510 | 0.4364 |
|
| 87 |
+
| 0.8962 | 3.59 | 825 | 0.7758 | 0.4342 |
|
| 88 |
+
| 0.4558 | 3.7 | 850 | 0.7314 | 0.4296 |
|
| 89 |
+
| 0.3476 | 3.81 | 875 | 0.6861 | 0.4153 |
|
| 90 |
+
| 0.3978 | 3.92 | 900 | 0.6961 | 0.4153 |
|
| 91 |
+
| 0.3818 | 4.03 | 925 | 0.6960 | 0.4071 |
|
| 92 |
+
| 0.2847 | 4.14 | 950 | 0.7222 | 0.4048 |
|
| 93 |
+
| 0.3997 | 4.25 | 975 | 0.6960 | 0.4191 |
|
| 94 |
+
| 0.2695 | 4.36 | 1000 | 0.6894 | 0.4138 |
|
| 95 |
+
| 0.4229 | 4.47 | 1025 | 0.7215 | 0.4304 |
|
| 96 |
+
| 0.2665 | 4.58 | 1050 | 0.7096 | 0.4056 |
|
| 97 |
+
| 0.3158 | 4.68 | 1075 | 0.6904 | 0.4153 |
|
| 98 |
+
| 0.2452 | 4.79 | 1100 | 0.6777 | 0.4071 |
|
| 99 |
+
| 0.3034 | 4.9 | 1125 | 0.6793 | 0.4048 |
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
### Framework versions
|
| 103 |
+
|
| 104 |
+
- Transformers 4.34.0
|
| 105 |
+
- Pytorch 2.0.1+cu118
|
| 106 |
+
- Datasets 2.14.5
|
| 107 |
+
- Tokenizers 0.14.1
|