End of training
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice_11_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: wav2vec2-large-xlsr-sw
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice_11_0
|
18 |
+
type: common_voice_11_0
|
19 |
+
config: sw
|
20 |
+
split: test
|
21 |
+
args: sw
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.3230712635221355
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# wav2vec2-large-xlsr-sw
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_11_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4334
|
36 |
+
- Wer: 0.3231
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0003
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 32
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 30
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
71 |
+
| 5.3405 | 0.88 | 400 | 2.8882 | 1.0000 |
|
72 |
+
| 1.083 | 1.77 | 800 | 0.5223 | 0.5849 |
|
73 |
+
| 0.4721 | 2.65 | 1200 | 0.3921 | 0.4667 |
|
74 |
+
| 0.3793 | 3.54 | 1600 | 0.3725 | 0.4257 |
|
75 |
+
| 0.3264 | 4.42 | 2000 | 0.3646 | 0.4179 |
|
76 |
+
| 0.294 | 5.31 | 2400 | 0.3542 | 0.4104 |
|
77 |
+
| 0.2623 | 6.19 | 2800 | 0.3576 | 0.3892 |
|
78 |
+
| 0.2408 | 7.08 | 3200 | 0.3516 | 0.3876 |
|
79 |
+
| 0.2229 | 7.96 | 3600 | 0.3580 | 0.3877 |
|
80 |
+
| 0.206 | 8.85 | 4000 | 0.3466 | 0.3683 |
|
81 |
+
| 0.1991 | 9.73 | 4400 | 0.3306 | 0.3783 |
|
82 |
+
| 0.1863 | 10.62 | 4800 | 0.3605 | 0.3707 |
|
83 |
+
| 0.1743 | 11.5 | 5200 | 0.3483 | 0.3703 |
|
84 |
+
| 0.1678 | 12.39 | 5600 | 0.3645 | 0.3618 |
|
85 |
+
| 0.1547 | 13.27 | 6000 | 0.3671 | 0.3589 |
|
86 |
+
| 0.152 | 14.16 | 6400 | 0.3733 | 0.3568 |
|
87 |
+
| 0.144 | 15.04 | 6800 | 0.3684 | 0.3486 |
|
88 |
+
| 0.136 | 15.93 | 7200 | 0.3558 | 0.3493 |
|
89 |
+
| 0.1262 | 16.81 | 7600 | 0.3748 | 0.3486 |
|
90 |
+
| 0.1222 | 17.7 | 8000 | 0.3774 | 0.3466 |
|
91 |
+
| 0.1164 | 18.58 | 8400 | 0.3840 | 0.3427 |
|
92 |
+
| 0.1108 | 19.47 | 8800 | 0.3988 | 0.3438 |
|
93 |
+
| 0.1072 | 20.35 | 9200 | 0.4020 | 0.3384 |
|
94 |
+
| 0.1008 | 21.24 | 9600 | 0.4013 | 0.3375 |
|
95 |
+
| 0.0982 | 22.12 | 10000 | 0.4162 | 0.3361 |
|
96 |
+
| 0.0951 | 23.01 | 10400 | 0.4107 | 0.3346 |
|
97 |
+
| 0.0923 | 23.89 | 10800 | 0.4248 | 0.3337 |
|
98 |
+
| 0.0866 | 24.78 | 11200 | 0.4151 | 0.3295 |
|
99 |
+
| 0.0875 | 25.66 | 11600 | 0.4211 | 0.3310 |
|
100 |
+
| 0.0813 | 26.55 | 12000 | 0.4303 | 0.3290 |
|
101 |
+
| 0.0775 | 27.43 | 12400 | 0.4334 | 0.3249 |
|
102 |
+
| 0.0759 | 28.32 | 12800 | 0.4312 | 0.3240 |
|
103 |
+
| 0.0758 | 29.2 | 13200 | 0.4334 | 0.3231 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.37.0.dev0
|
109 |
+
- Pytorch 2.1.1+cu121
|
110 |
+
- Datasets 2.16.1
|
111 |
+
- 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 1262057580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f332d78ad476eebb800e79cefa9c5c2d7f8bda1e6b69e366e135e02083708668
|
3 |
size 1262057580
|
runs/Jan16_16-42-18_hades-prod01/events.out.tfevents.1705423625.hades-prod01.1678284.0
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 sha256:4fba4499a661112f10904e03ed48b63f95d654bcadb4ae8514bd73bdbe6bf08f
|
3 |
+
size 22072
|