End of training
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: jonatasgrosman/wav2vec2-xls-r-1b-french
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: xls_1b_decoding_fr_decoding_test_iter
|
| 8 |
results: []
|
|
@@ -17,7 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/danakal/xls_300m_french_data/runs/cf8f5rsv)
|
| 18 |
# xls_1b_decoding_fr_decoding_test_iter
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-xls-r-1b-french](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-french) on
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -48,6 +53,58 @@ The following hyperparameters were used during training:
|
|
| 48 |
- num_epochs: 30
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.43.0.dev0
|
|
|
|
| 3 |
base_model: jonatasgrosman/wav2vec2-xls-r-1b-french
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
- name: xls_1b_decoding_fr_decoding_test_iter
|
| 10 |
results: []
|
|
|
|
| 19 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/danakal/xls_300m_french_data/runs/cf8f5rsv)
|
| 20 |
# xls_1b_decoding_fr_decoding_test_iter
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-xls-r-1b-french](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-french) on the None dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.7122
|
| 25 |
+
- Wer: 0.4249
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 53 |
- num_epochs: 30
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 59 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 60 |
+
| 1.2189 | 0.6452 | 40 | 0.6929 | 0.6997 |
|
| 61 |
+
| 0.6612 | 1.2903 | 80 | 0.5628 | 0.5886 |
|
| 62 |
+
| 0.5586 | 1.9355 | 120 | 0.4900 | 0.5202 |
|
| 63 |
+
| 0.4528 | 2.5806 | 160 | 0.4671 | 0.4960 |
|
| 64 |
+
| 0.3799 | 3.2258 | 200 | 0.4555 | 0.4812 |
|
| 65 |
+
| 0.3638 | 3.8710 | 240 | 0.4534 | 0.4686 |
|
| 66 |
+
| 0.3035 | 4.5161 | 280 | 0.4709 | 0.4575 |
|
| 67 |
+
| 0.2905 | 5.1613 | 320 | 0.4640 | 0.4551 |
|
| 68 |
+
| 0.2599 | 5.8065 | 360 | 0.4629 | 0.4444 |
|
| 69 |
+
| 0.2095 | 6.4516 | 400 | 0.4966 | 0.4598 |
|
| 70 |
+
| 0.2206 | 7.0968 | 440 | 0.4958 | 0.4496 |
|
| 71 |
+
| 0.1921 | 7.7419 | 480 | 0.4944 | 0.4389 |
|
| 72 |
+
| 0.1946 | 8.3871 | 520 | 0.5035 | 0.4542 |
|
| 73 |
+
| 0.1629 | 9.0323 | 560 | 0.4978 | 0.4430 |
|
| 74 |
+
| 0.15 | 9.6774 | 600 | 0.5143 | 0.4449 |
|
| 75 |
+
| 0.1402 | 10.3226 | 640 | 0.5550 | 0.4351 |
|
| 76 |
+
| 0.1351 | 10.9677 | 680 | 0.5548 | 0.4319 |
|
| 77 |
+
| 0.1212 | 11.6129 | 720 | 0.5455 | 0.4291 |
|
| 78 |
+
| 0.1243 | 12.2581 | 760 | 0.5773 | 0.4300 |
|
| 79 |
+
| 0.1035 | 12.9032 | 800 | 0.5636 | 0.4407 |
|
| 80 |
+
| 0.1103 | 13.5484 | 840 | 0.6062 | 0.4245 |
|
| 81 |
+
| 0.0879 | 14.1935 | 880 | 0.5990 | 0.4384 |
|
| 82 |
+
| 0.0947 | 14.8387 | 920 | 0.5905 | 0.4426 |
|
| 83 |
+
| 0.0804 | 15.4839 | 960 | 0.6118 | 0.4412 |
|
| 84 |
+
| 0.0921 | 16.1290 | 1000 | 0.6040 | 0.4435 |
|
| 85 |
+
| 0.0816 | 16.7742 | 1040 | 0.6188 | 0.4170 |
|
| 86 |
+
| 0.0715 | 17.4194 | 1080 | 0.6463 | 0.4268 |
|
| 87 |
+
| 0.0799 | 18.0645 | 1120 | 0.6326 | 0.4351 |
|
| 88 |
+
| 0.0631 | 18.7097 | 1160 | 0.6526 | 0.4314 |
|
| 89 |
+
| 0.0643 | 19.3548 | 1200 | 0.6502 | 0.4254 |
|
| 90 |
+
| 0.0537 | 20.0 | 1240 | 0.6922 | 0.4310 |
|
| 91 |
+
| 0.0628 | 20.6452 | 1280 | 0.6778 | 0.4286 |
|
| 92 |
+
| 0.0527 | 21.2903 | 1320 | 0.6765 | 0.4324 |
|
| 93 |
+
| 0.0566 | 21.9355 | 1360 | 0.6843 | 0.4249 |
|
| 94 |
+
| 0.0533 | 22.5806 | 1400 | 0.7073 | 0.4277 |
|
| 95 |
+
| 0.052 | 23.2258 | 1440 | 0.7048 | 0.4296 |
|
| 96 |
+
| 0.0473 | 23.8710 | 1480 | 0.6886 | 0.4226 |
|
| 97 |
+
| 0.0502 | 24.5161 | 1520 | 0.6940 | 0.4258 |
|
| 98 |
+
| 0.0496 | 25.1613 | 1560 | 0.6839 | 0.4240 |
|
| 99 |
+
| 0.0435 | 25.8065 | 1600 | 0.6931 | 0.4207 |
|
| 100 |
+
| 0.0394 | 26.4516 | 1640 | 0.7002 | 0.4235 |
|
| 101 |
+
| 0.047 | 27.0968 | 1680 | 0.7086 | 0.4212 |
|
| 102 |
+
| 0.0439 | 27.7419 | 1720 | 0.7124 | 0.4272 |
|
| 103 |
+
| 0.0375 | 28.3871 | 1760 | 0.7166 | 0.4245 |
|
| 104 |
+
| 0.0444 | 29.0323 | 1800 | 0.7149 | 0.4240 |
|
| 105 |
+
| 0.0421 | 29.6774 | 1840 | 0.7122 | 0.4249 |
|
| 106 |
+
|
| 107 |
+
|
| 108 |
### Framework versions
|
| 109 |
|
| 110 |
- Transformers 4.43.0.dev0
|