Model save
Browse files- README.md +82 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: xls-r-1b-bem-genbed-all
|
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 |
+
# xls-r-1b-bem-genbed-all
|
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: 0.2316
|
22 |
+
- Wer: 0.7116
|
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: 5e-05
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
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 |
+
| 4.6827 | 0.2644 | 200 | 2.8347 | 1.0 |
|
58 |
+
| 1.0401 | 0.5288 | 400 | 0.5636 | 0.9410 |
|
59 |
+
| 0.4289 | 0.7931 | 600 | 0.4018 | 0.9029 |
|
60 |
+
| 0.3449 | 1.0575 | 800 | 0.3604 | 0.8771 |
|
61 |
+
| 0.2954 | 1.3219 | 1000 | 0.3389 | 0.8741 |
|
62 |
+
| 0.2719 | 1.5863 | 1200 | 0.2962 | 0.8439 |
|
63 |
+
| 0.2472 | 1.8506 | 1400 | 0.2701 | 0.8053 |
|
64 |
+
| 0.2093 | 2.1150 | 1600 | 0.2599 | 0.8285 |
|
65 |
+
| 0.1725 | 2.3794 | 1800 | 0.2534 | 0.8375 |
|
66 |
+
| 0.1675 | 2.6438 | 2000 | 0.2406 | 0.7691 |
|
67 |
+
| 0.1632 | 2.9081 | 2200 | 0.2309 | 0.7616 |
|
68 |
+
| 0.1295 | 3.1725 | 2400 | 0.2387 | 0.7557 |
|
69 |
+
| 0.1082 | 3.4369 | 2600 | 0.2275 | 0.7329 |
|
70 |
+
| 0.1059 | 3.7013 | 2800 | 0.2240 | 0.7329 |
|
71 |
+
| 0.1049 | 3.9656 | 3000 | 0.2172 | 0.7294 |
|
72 |
+
| 0.0657 | 4.2300 | 3200 | 0.2320 | 0.7220 |
|
73 |
+
| 0.059 | 4.4944 | 3400 | 0.2341 | 0.7215 |
|
74 |
+
| 0.0582 | 4.7588 | 3600 | 0.2316 | 0.7116 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.45.0.dev0
|
80 |
+
- Pytorch 2.4.0+cu121
|
81 |
+
- Datasets 2.21.0
|
82 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3850244620
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac5d7c088bd5a3da10416d32d85db5f7c8431e48ef4df9264ab5806f5d39b88d
|
3 |
size 3850244620
|