Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-xls-r-1b
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wav2vec2-xslr-tr-testv2
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wav2vec2-xslr-tr-testv2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2789
|
| 22 |
+
- Wer: 0.4783
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 5.0
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 57 |
+
| No log | 0.1375 | 100 | 2.9646 | 1.0 |
|
| 58 |
+
| No log | 0.2749 | 200 | 0.9689 | 0.9848 |
|
| 59 |
+
| No log | 0.4124 | 300 | 0.8561 | 0.9170 |
|
| 60 |
+
| No log | 0.5498 | 400 | 0.7970 | 0.912 |
|
| 61 |
+
| 1.9898 | 0.6873 | 500 | 0.8464 | 0.9258 |
|
| 62 |
+
| 1.9898 | 0.8247 | 600 | 0.7358 | 0.8872 |
|
| 63 |
+
| 1.9898 | 0.9622 | 700 | 0.6374 | 0.8608 |
|
| 64 |
+
| 1.9898 | 1.0997 | 800 | 0.5180 | 0.7297 |
|
| 65 |
+
| 1.9898 | 1.2371 | 900 | 0.4852 | 0.7212 |
|
| 66 |
+
| 0.663 | 1.3746 | 1000 | 0.4840 | 0.7278 |
|
| 67 |
+
| 0.663 | 1.5120 | 1100 | 0.4626 | 0.7135 |
|
| 68 |
+
| 0.663 | 1.6495 | 1200 | 0.4493 | 0.676 |
|
| 69 |
+
| 0.663 | 1.7869 | 1300 | 0.4419 | 0.6813 |
|
| 70 |
+
| 0.663 | 1.9244 | 1400 | 0.4306 | 0.6749 |
|
| 71 |
+
| 0.5455 | 2.0619 | 1500 | 0.4329 | 0.6846 |
|
| 72 |
+
| 0.5455 | 2.1993 | 1600 | 0.4227 | 0.6685 |
|
| 73 |
+
| 0.5455 | 2.3368 | 1700 | 0.4097 | 0.6472 |
|
| 74 |
+
| 0.5455 | 2.4742 | 1800 | 0.4035 | 0.6343 |
|
| 75 |
+
| 0.5455 | 2.6117 | 1900 | 0.4041 | 0.6304 |
|
| 76 |
+
| 0.433 | 2.7491 | 2000 | 0.3962 | 0.6542 |
|
| 77 |
+
| 0.433 | 2.8866 | 2100 | 0.3601 | 0.6041 |
|
| 78 |
+
| 0.433 | 3.0241 | 2200 | 0.3473 | 0.5864 |
|
| 79 |
+
| 0.433 | 3.1615 | 2300 | 0.3456 | 0.5723 |
|
| 80 |
+
| 0.433 | 3.2990 | 2400 | 0.3380 | 0.5617 |
|
| 81 |
+
| 0.3509 | 3.4364 | 2500 | 0.3267 | 0.5563 |
|
| 82 |
+
| 0.3509 | 3.5739 | 2600 | 0.3208 | 0.5570 |
|
| 83 |
+
| 0.3509 | 3.7113 | 2700 | 0.3124 | 0.5397 |
|
| 84 |
+
| 0.3509 | 3.8488 | 2800 | 0.3038 | 0.5272 |
|
| 85 |
+
| 0.3509 | 3.9863 | 2900 | 0.2994 | 0.5254 |
|
| 86 |
+
| 0.2871 | 4.1237 | 3000 | 0.3073 | 0.5247 |
|
| 87 |
+
| 0.2871 | 4.2612 | 3100 | 0.3009 | 0.5122 |
|
| 88 |
+
| 0.2871 | 4.3986 | 3200 | 0.2975 | 0.4953 |
|
| 89 |
+
| 0.2871 | 4.5361 | 3300 | 0.2898 | 0.4938 |
|
| 90 |
+
| 0.2871 | 4.6735 | 3400 | 0.2835 | 0.4902 |
|
| 91 |
+
| 0.2198 | 4.8110 | 3500 | 0.2804 | 0.4802 |
|
| 92 |
+
| 0.2198 | 4.9485 | 3600 | 0.2789 | 0.4783 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.46.0.dev0
|
| 98 |
+
- Pytorch 2.4.1+cu121
|
| 99 |
+
- Datasets 3.0.1
|
| 100 |
+
- Tokenizers 0.20.0
|
runs/Sep26_10-16-45_6164405edb41/events.out.tfevents.1727345834.6164405edb41.25030.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:284edc11f86f9a6f08f74153a5050e488912763cc1092fcc1d051c162fd47e3a
|
| 3 |
+
size 19660
|