End of training
Browse files
README.md
CHANGED
|
@@ -6,10 +6,10 @@ base_model: openai/whisper-tiny
|
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
|
|
|
| 9 |
- dsfsi-anv/multilingual-nchlt-dataset
|
| 10 |
-
- andreoosthuizen/afrikaans-30s
|
| 11 |
- voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans
|
| 12 |
-
-
|
| 13 |
metrics:
|
| 14 |
- wer
|
| 15 |
model-index:
|
|
@@ -20,15 +20,16 @@ model-index:
|
|
| 20 |
type: automatic-speech-recognition
|
| 21 |
dataset:
|
| 22 |
name: Common Voice 17.0
|
| 23 |
-
type:
|
| 24 |
config: af_za
|
| 25 |
split: test
|
| 26 |
args: af_za
|
| 27 |
metrics:
|
| 28 |
- name: Wer
|
| 29 |
type: wer
|
| 30 |
-
value: 45.
|
| 31 |
---
|
|
|
|
| 32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 33 |
should probably proofread and complete it, then remove this comment. -->
|
| 34 |
|
|
@@ -36,9 +37,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 36 |
|
| 37 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
-
- Loss: 1.
|
| 40 |
-
- Wer: 45.
|
| 41 |
-
- Cer: 18.
|
| 42 |
|
| 43 |
## Model description
|
| 44 |
|
|
@@ -70,66 +71,66 @@ The following hyperparameters were used during training:
|
|
| 70 |
|
| 71 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 72 |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.1619 | 0.1667 | 1000 | 1.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.0973 | 0.2333 | 1400 | 1.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.0503 | 0.3833 | 2300 | 1.
|
| 96 |
-
| 0.0497 | 0.4 | 2400 | 1.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.0497 | 0.45 | 2700 | 1.
|
| 100 |
-
| 0.0403 | 0.4667 | 2800 | 1.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.0375 | 0.6 | 3600 | 1.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.0197 | 0.6333 | 3800 | 1.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.0245 | 1.0235 | 4000 | 1.
|
| 113 |
-
| 0.0146 | 1.0402 | 4100 | 1.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.0271 | 1.0902 | 4400 | 1.
|
| 117 |
-
| 0.0237 | 1.1068 | 4500 | 1.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.0366 | 1.1402 | 4700 | 1.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.0264 | 1.1902 | 5000 | 1.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.0162 | 1.2235 | 5200 | 1.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.0214 | 1.2568 | 5400 | 1.
|
| 127 |
-
| 0.0163 | 1.2735 | 5500 | 1.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.0134 | 1.3235 | 5800 | 1.
|
| 131 |
-
| 0.0137 | 1.3402 | 5900 | 1.
|
| 132 |
-
| 0.0174 | 1.3568 | 6000 | 1.
|
| 133 |
|
| 134 |
|
| 135 |
### Framework versions
|
|
@@ -138,16 +139,3 @@ The following hyperparameters were used during training:
|
|
| 138 |
- Pytorch 2.3.0+cu121
|
| 139 |
- Datasets 2.19.1
|
| 140 |
- Tokenizers 0.19.1
|
| 141 |
-
|
| 142 |
-
## Citation
|
| 143 |
-
|
| 144 |
-
Please cite the model using the following BibTeX entry:
|
| 145 |
-
|
| 146 |
-
```bibtex
|
| 147 |
-
@misc{deepdml/whisper-tiny-af-mix-norm,
|
| 148 |
-
title={Fine-tuned Whisper tiny ASR model for speech recognition in Afrikaans},
|
| 149 |
-
author={Jimenez, David},
|
| 150 |
-
howpublished={\url{https://huggingface.co/deepdml/whisper-tiny-af-mix-norm}},
|
| 151 |
-
year={2026}
|
| 152 |
-
}
|
| 153 |
-
```
|
|
|
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
+
- google/fleurs
|
| 10 |
- dsfsi-anv/multilingual-nchlt-dataset
|
|
|
|
| 11 |
- voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans
|
| 12 |
+
- andreoosthuizen/afrikaans-30s
|
| 13 |
metrics:
|
| 14 |
- wer
|
| 15 |
model-index:
|
|
|
|
| 20 |
type: automatic-speech-recognition
|
| 21 |
dataset:
|
| 22 |
name: Common Voice 17.0
|
| 23 |
+
type: google/fleurs
|
| 24 |
config: af_za
|
| 25 |
split: test
|
| 26 |
args: af_za
|
| 27 |
metrics:
|
| 28 |
- name: Wer
|
| 29 |
type: wer
|
| 30 |
+
value: 45.17581846526936
|
| 31 |
---
|
| 32 |
+
|
| 33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 34 |
should probably proofread and complete it, then remove this comment. -->
|
| 35 |
|
|
|
|
| 37 |
|
| 38 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
|
| 39 |
It achieves the following results on the evaluation set:
|
| 40 |
+
- Loss: 1.2813
|
| 41 |
+
- Wer: 45.1758
|
| 42 |
+
- Cer: 18.4153
|
| 43 |
|
| 44 |
## Model description
|
| 45 |
|
|
|
|
| 71 |
|
| 72 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 73 |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
|
| 74 |
+
| 1.9201 | 0.0167 | 100 | 1.9214 | 75.4201 | 31.6653 |
|
| 75 |
+
| 1.0858 | 0.0333 | 200 | 1.3963 | 56.0714 | 22.9766 |
|
| 76 |
+
| 0.6925 | 0.05 | 300 | 1.2245 | 50.4417 | 19.7579 |
|
| 77 |
+
| 0.5015 | 0.0667 | 400 | 1.1657 | 48.4150 | 19.2009 |
|
| 78 |
+
| 0.3938 | 0.0833 | 500 | 1.1385 | 46.9773 | 18.5355 |
|
| 79 |
+
| 0.2988 | 0.1 | 600 | 1.1282 | 47.6529 | 20.0862 |
|
| 80 |
+
| 0.2636 | 0.1167 | 700 | 1.1273 | 47.9993 | 20.5523 |
|
| 81 |
+
| 0.2127 | 0.1333 | 800 | 1.1218 | 47.5489 | 19.8868 |
|
| 82 |
+
| 0.1874 | 0.15 | 900 | 1.1289 | 46.9080 | 20.8542 |
|
| 83 |
+
| 0.1619 | 0.1667 | 1000 | 1.1330 | 49.1945 | 21.9476 |
|
| 84 |
+
| 0.1337 | 0.1833 | 1100 | 1.1491 | 47.5489 | 20.1302 |
|
| 85 |
+
| 0.1131 | 0.2 | 1200 | 1.1537 | 48.6575 | 20.8630 |
|
| 86 |
+
| 0.1051 | 0.2167 | 1300 | 1.1685 | 50.3897 | 21.0037 |
|
| 87 |
+
| 0.0973 | 0.2333 | 1400 | 1.1724 | 45.0719 | 18.5941 |
|
| 88 |
+
| 0.0939 | 0.25 | 1500 | 1.1687 | 44.3963 | 17.9023 |
|
| 89 |
+
| 0.0729 | 0.2667 | 1600 | 1.1577 | 48.2418 | 20.3764 |
|
| 90 |
+
| 0.0798 | 0.2833 | 1700 | 1.1849 | 48.9174 | 20.8894 |
|
| 91 |
+
| 0.0622 | 0.3 | 1800 | 1.1850 | 43.3397 | 17.7938 |
|
| 92 |
+
| 0.0608 | 0.3167 | 1900 | 1.1882 | 44.0499 | 18.2540 |
|
| 93 |
+
| 0.0567 | 0.3333 | 2000 | 1.1892 | 43.4609 | 17.9140 |
|
| 94 |
+
| 0.0515 | 0.35 | 2100 | 1.1929 | 46.2151 | 18.8051 |
|
| 95 |
+
| 0.0542 | 0.3667 | 2200 | 1.2082 | 44.3963 | 18.3918 |
|
| 96 |
+
| 0.0503 | 0.3833 | 2300 | 1.1946 | 47.9820 | 19.6553 |
|
| 97 |
+
| 0.0497 | 0.4 | 2400 | 1.1912 | 49.7662 | 21.5841 |
|
| 98 |
+
| 0.0495 | 0.4167 | 2500 | 1.2044 | 47.2718 | 18.8491 |
|
| 99 |
+
| 0.0338 | 0.4333 | 2600 | 1.2134 | 43.8940 | 17.4303 |
|
| 100 |
+
| 0.0497 | 0.45 | 2700 | 1.2063 | 46.1632 | 18.7553 |
|
| 101 |
+
| 0.0403 | 0.4667 | 2800 | 1.2163 | 46.7868 | 18.9605 |
|
| 102 |
+
| 0.0363 | 0.4833 | 2900 | 1.2167 | 43.0972 | 17.1782 |
|
| 103 |
+
| 0.0361 | 0.5 | 3000 | 1.2261 | 46.4403 | 18.8169 |
|
| 104 |
+
| 0.0365 | 0.5167 | 3100 | 1.2220 | 42.6641 | 18.1280 |
|
| 105 |
+
| 0.0277 | 0.5333 | 3200 | 1.2331 | 46.3191 | 18.8227 |
|
| 106 |
+
| 0.0333 | 0.55 | 3300 | 1.2272 | 43.5822 | 17.4215 |
|
| 107 |
+
| 0.0315 | 0.5667 | 3400 | 1.2376 | 46.4750 | 18.9928 |
|
| 108 |
+
| 0.0285 | 0.5833 | 3500 | 1.2420 | 43.4263 | 17.3482 |
|
| 109 |
+
| 0.0375 | 0.6 | 3600 | 1.2388 | 46.6309 | 18.5530 |
|
| 110 |
+
| 0.0229 | 0.6167 | 3700 | 1.2376 | 42.7854 | 17.0287 |
|
| 111 |
+
| 0.0197 | 0.6333 | 3800 | 1.2449 | 43.4263 | 17.2251 |
|
| 112 |
+
| 0.0186 | 1.0068 | 3900 | 1.2528 | 46.5789 | 18.6791 |
|
| 113 |
+
| 0.0245 | 1.0235 | 4000 | 1.2527 | 49.3851 | 21.7219 |
|
| 114 |
+
| 0.0146 | 1.0402 | 4100 | 1.2579 | 41.9886 | 17.1518 |
|
| 115 |
+
| 0.0137 | 1.0568 | 4200 | 1.2673 | 43.2877 | 17.0932 |
|
| 116 |
+
| 0.0244 | 1.0735 | 4300 | 1.2768 | 46.5443 | 18.9957 |
|
| 117 |
+
| 0.0271 | 1.0902 | 4400 | 1.2655 | 46.2325 | 18.7319 |
|
| 118 |
+
| 0.0237 | 1.1068 | 4500 | 1.2803 | 46.5616 | 18.5237 |
|
| 119 |
+
| 0.0212 | 1.1235 | 4600 | 1.2725 | 48.3804 | 20.5171 |
|
| 120 |
+
| 0.0366 | 1.1402 | 4700 | 1.2623 | 46.6482 | 19.9777 |
|
| 121 |
+
| 0.0278 | 1.1568 | 4800 | 1.2632 | 45.4010 | 18.4211 |
|
| 122 |
+
| 0.0232 | 1.1735 | 4900 | 1.2652 | 45.5223 | 18.5501 |
|
| 123 |
+
| 0.0264 | 1.1902 | 5000 | 1.2720 | 43.0799 | 17.3043 |
|
| 124 |
+
| 0.0244 | 1.2068 | 5100 | 1.2714 | 44.2058 | 18.3625 |
|
| 125 |
+
| 0.0162 | 1.2235 | 5200 | 1.2697 | 45.3144 | 18.4827 |
|
| 126 |
+
| 0.0203 | 1.2402 | 5300 | 1.2812 | 43.2358 | 17.0727 |
|
| 127 |
+
| 0.0214 | 1.2568 | 5400 | 1.2804 | 42.7681 | 16.8939 |
|
| 128 |
+
| 0.0163 | 1.2735 | 5500 | 1.2834 | 45.8341 | 18.4416 |
|
| 129 |
+
| 0.0149 | 1.2902 | 5600 | 1.2833 | 45.5049 | 18.4915 |
|
| 130 |
+
| 0.0196 | 1.3068 | 5700 | 1.2822 | 46.0592 | 18.8491 |
|
| 131 |
+
| 0.0134 | 1.3235 | 5800 | 1.2807 | 46.0073 | 18.8462 |
|
| 132 |
+
| 0.0137 | 1.3402 | 5900 | 1.2803 | 42.5775 | 17.1694 |
|
| 133 |
+
| 0.0174 | 1.3568 | 6000 | 1.2813 | 45.1758 | 18.4153 |
|
| 134 |
|
| 135 |
|
| 136 |
### Framework versions
|
|
|
|
| 139 |
- Pytorch 2.3.0+cu121
|
| 140 |
- Datasets 2.19.1
|
| 141 |
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|