End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: tun_msa_wav2vec4
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# tun_msa_wav2vec4
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.0258
|
| 19 |
+
- Wer: 0.7054
|
| 20 |
+
- Cer: 0.2514
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-06
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 700
|
| 46 |
+
- num_epochs: 60
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 51 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
|
| 52 |
+
| 4.9443 | 6.7669 | 900 | 2.9731 | 0.9978 | 0.9143 |
|
| 53 |
+
| 2.385 | 13.5338 | 1800 | 1.4747 | 0.8366 | 0.3285 |
|
| 54 |
+
| 1.6027 | 20.3008 | 2700 | 1.1810 | 0.7617 | 0.2766 |
|
| 55 |
+
| 1.3459 | 27.0677 | 3600 | 1.0963 | 0.7317 | 0.2615 |
|
| 56 |
+
| 1.2812 | 33.8346 | 4500 | 1.0580 | 0.7240 | 0.2563 |
|
| 57 |
+
| 1.2156 | 40.6015 | 5400 | 1.0426 | 0.7127 | 0.2538 |
|
| 58 |
+
| 1.1119 | 47.3684 | 6300 | 1.0305 | 0.7069 | 0.2519 |
|
| 59 |
+
| 1.0993 | 54.1353 | 7200 | 1.0258 | 0.7054 | 0.2514 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.41.2
|
| 65 |
+
- Pytorch 2.1.2
|
| 66 |
+
- Datasets 2.19.2
|
| 67 |
+
- Tokenizers 0.19.1
|
runs/Aug05_08-32-03_bce6df901103/events.out.tfevents.1722846729.bce6df901103.34.0
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 sha256:3a0becb7aa48e1129c4a4ad2b17ce8f79dcad436e8ffcacc9a5b4d5b50f32efc
|
| 3 |
+
size 11574
|