Model save
Browse files- README.md +99 -2
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,3 +1,100 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: alamsher/wav2vec2-large-xlsr-53-common-voice-sw
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- common_voice_17_0
|
| 9 |
+
metrics:
|
| 10 |
+
- wer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: model
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Automatic Speech Recognition
|
| 16 |
+
type: automatic-speech-recognition
|
| 17 |
+
dataset:
|
| 18 |
+
name: common_voice_17_0
|
| 19 |
+
type: common_voice_17_0
|
| 20 |
+
config: sw
|
| 21 |
+
split: validation
|
| 22 |
+
args: sw
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Wer
|
| 25 |
+
type: wer
|
| 26 |
+
value: 0.18270008084074374
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# model
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [alamsher/wav2vec2-large-xlsr-53-common-voice-sw](https://huggingface.co/alamsher/wav2vec2-large-xlsr-53-common-voice-sw) on the common_voice_17_0 dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.2929
|
| 37 |
+
- Wer: 0.1827
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 3e-05
|
| 57 |
+
- train_batch_size: 8
|
| 58 |
+
- eval_batch_size: 4
|
| 59 |
+
- seed: 42
|
| 60 |
+
- gradient_accumulation_steps: 2
|
| 61 |
+
- total_train_batch_size: 16
|
| 62 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 65 |
+
- num_epochs: 15
|
| 66 |
+
- mixed_precision_training: Native AMP
|
| 67 |
+
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
| 72 |
+
| 0.2938 | 0.5028 | 500 | 0.3439 | 0.1940 |
|
| 73 |
+
| 0.273 | 1.0050 | 1000 | 0.3088 | 0.1923 |
|
| 74 |
+
| 0.2327 | 1.5078 | 1500 | 0.3031 | 0.1907 |
|
| 75 |
+
| 0.2351 | 2.0101 | 2000 | 0.2877 | 0.1897 |
|
| 76 |
+
| 0.2213 | 2.5128 | 2500 | 0.2915 | 0.1889 |
|
| 77 |
+
| 0.2172 | 3.0151 | 3000 | 0.2863 | 0.1879 |
|
| 78 |
+
| 0.191 | 3.5178 | 3500 | 0.2881 | 0.1880 |
|
| 79 |
+
| 0.2048 | 4.0201 | 4000 | 0.2832 | 0.1875 |
|
| 80 |
+
| 0.1928 | 4.5229 | 4500 | 0.2825 | 0.1863 |
|
| 81 |
+
| 0.1871 | 5.0251 | 5000 | 0.2861 | 0.1863 |
|
| 82 |
+
| 0.1856 | 5.5279 | 5500 | 0.2856 | 0.1856 |
|
| 83 |
+
| 0.1763 | 6.0302 | 6000 | 0.2854 | 0.1856 |
|
| 84 |
+
| 0.1707 | 6.5329 | 6500 | 0.2883 | 0.1853 |
|
| 85 |
+
| 0.1714 | 7.0352 | 7000 | 0.2849 | 0.1850 |
|
| 86 |
+
| 0.1577 | 7.5380 | 7500 | 0.2875 | 0.1851 |
|
| 87 |
+
| 0.162 | 8.0402 | 8000 | 0.2852 | 0.1850 |
|
| 88 |
+
| 0.1489 | 8.5430 | 8500 | 0.2911 | 0.1833 |
|
| 89 |
+
| 0.1674 | 9.0452 | 9000 | 0.2887 | 0.1826 |
|
| 90 |
+
| 0.1818 | 9.5480 | 9500 | 0.2894 | 0.1828 |
|
| 91 |
+
| 0.165 | 10.0503 | 10000 | 0.2915 | 0.1830 |
|
| 92 |
+
| 0.1715 | 10.5530 | 10500 | 0.2929 | 0.1827 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.52.4
|
| 98 |
+
- Pytorch 2.6.0+cu124
|
| 99 |
+
- Datasets 3.6.0
|
| 100 |
+
- Tokenizers 0.21.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262049380
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ee2ae8470cbd3c613b196523cb1f0dbeaad660a9eb19a0eb035e2dc59815f03
|
| 3 |
size 1262049380
|