End of training
Browse files
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: wav2vec2-large-xls-r-300m
|
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 |
+
# wav2vec2-large-xls-r-300m
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 3.6299
|
19 |
+
- Cer: 69.5709
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 5
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
52 |
+
| 56.9189 | 0.13 | 200 | 17.3335 | 100.0 |
|
53 |
+
| 24.9477 | 0.26 | 400 | 5.2898 | 93.4002 |
|
54 |
+
| 22.4883 | 0.39 | 600 | 5.1855 | 91.7503 |
|
55 |
+
| 23.6577 | 0.52 | 800 | 5.5828 | 93.8097 |
|
56 |
+
| 12.0508 | 0.64 | 1000 | 5.5876 | 92.9788 |
|
57 |
+
| 6.9102 | 0.77 | 1200 | 5.2180 | 93.1153 |
|
58 |
+
| 5.2937 | 0.9 | 1400 | 4.6411 | 93.6613 |
|
59 |
+
| 4.6224 | 1.03 | 1600 | 4.7614 | 93.7088 |
|
60 |
+
| 4.6148 | 1.16 | 1800 | 4.8569 | 93.0916 |
|
61 |
+
| 4.6129 | 1.29 | 2000 | 4.6641 | 92.5693 |
|
62 |
+
| 4.5837 | 1.42 | 2200 | 4.7341 | 93.5664 |
|
63 |
+
| 4.5465 | 1.55 | 2400 | 4.7580 | 93.3646 |
|
64 |
+
| 4.5042 | 1.68 | 2600 | 4.8342 | 93.4180 |
|
65 |
+
| 4.4535 | 1.81 | 2800 | 4.8323 | 93.4952 |
|
66 |
+
| 4.3942 | 1.93 | 3000 | 4.7891 | 92.1538 |
|
67 |
+
| 4.347 | 2.06 | 3200 | 4.5461 | 92.4150 |
|
68 |
+
| 4.3064 | 2.19 | 3400 | 4.7049 | 92.0114 |
|
69 |
+
| 4.301 | 2.32 | 3600 | 4.6162 | 92.3438 |
|
70 |
+
| 4.2107 | 2.45 | 3800 | 4.5264 | 92.3497 |
|
71 |
+
| 4.1768 | 2.58 | 4000 | 4.4067 | 87.1090 |
|
72 |
+
| 4.1395 | 2.71 | 4200 | 4.5684 | 90.6048 |
|
73 |
+
| 4.0568 | 2.84 | 4400 | 4.4142 | 87.7856 |
|
74 |
+
| 4.0007 | 2.97 | 4600 | 4.2861 | 87.7619 |
|
75 |
+
| 3.9426 | 3.09 | 4800 | 4.2750 | 87.4236 |
|
76 |
+
| 3.8207 | 3.22 | 5000 | 4.2217 | 84.2424 |
|
77 |
+
| 3.7678 | 3.35 | 5200 | 4.1129 | 81.1324 |
|
78 |
+
| 3.7522 | 3.48 | 5400 | 4.0891 | 83.2512 |
|
79 |
+
| 3.6666 | 3.61 | 5600 | 4.0328 | 80.0107 |
|
80 |
+
| 3.587 | 3.74 | 5800 | 4.0241 | 80.2837 |
|
81 |
+
| 3.5184 | 3.87 | 6000 | 4.0116 | 81.8209 |
|
82 |
+
| 3.449 | 4.0 | 6200 | 3.9031 | 76.4437 |
|
83 |
+
| 3.3503 | 4.13 | 6400 | 3.8643 | 75.8680 |
|
84 |
+
| 3.2541 | 4.26 | 6600 | 3.8508 | 72.4850 |
|
85 |
+
| 3.1987 | 4.38 | 6800 | 3.8425 | 71.8203 |
|
86 |
+
| 3.1435 | 4.51 | 7000 | 3.7289 | 71.6719 |
|
87 |
+
| 3.0583 | 4.64 | 7200 | 3.6855 | 70.1703 |
|
88 |
+
| 3.0443 | 4.77 | 7400 | 3.6365 | 69.6540 |
|
89 |
+
| 3.0508 | 4.9 | 7600 | 3.6299 | 69.5709 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.35.2
|
95 |
+
- Pytorch 2.1.0+cu121
|
96 |
+
- Datasets 2.16.0
|
97 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1266842296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43a2690d03976b7345d6a8a30312775a80320cf09ef9cac99ec999c55003f91c
|
3 |
size 1266842296
|
runs/Dec26_02-45-35_2f7c798edc1a/events.out.tfevents.1703559148.2f7c798edc1a.6021.0
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 sha256:976c461c282c720ae496c8b9c8ec2b2d19c618676c3dc741c3b88cd17777e8ed
|
3 |
+
size 24094
|