End of training
Browse files
README.md
ADDED
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice_13_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: wav2vec2-large-xls-r-300m-gn-pt
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice_13_0
|
18 |
+
type: common_voice_13_0
|
19 |
+
config: gn
|
20 |
+
split: test
|
21 |
+
args: gn
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.5431804645622395
|
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-xls-r-300m-gn-pt
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6822
|
36 |
+
- Wer: 0.5432
|
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: 100
|
64 |
+
- num_epochs: 35
|
65 |
+
- mixed_precision_training: Native AMP
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
71 |
+
| 4.1972 | 0.79 | 400 | 1.9288 | 1.0045 |
|
72 |
+
| 0.9928 | 1.58 | 800 | 0.8247 | 0.9452 |
|
73 |
+
| 0.6075 | 2.36 | 1200 | 0.7675 | 0.8451 |
|
74 |
+
| 0.4724 | 3.15 | 1600 | 0.5485 | 0.7111 |
|
75 |
+
| 0.3879 | 3.94 | 2000 | 0.5885 | 0.7433 |
|
76 |
+
| 0.3152 | 4.73 | 2400 | 0.7606 | 0.7695 |
|
77 |
+
| 0.2872 | 5.52 | 2800 | 0.5723 | 0.6608 |
|
78 |
+
| 0.258 | 6.31 | 3200 | 0.5971 | 0.6820 |
|
79 |
+
| 0.2317 | 7.09 | 3600 | 0.5845 | 0.6471 |
|
80 |
+
| 0.2137 | 7.88 | 4000 | 0.7690 | 0.7198 |
|
81 |
+
| 0.193 | 8.67 | 4400 | 0.6219 | 0.6614 |
|
82 |
+
| 0.1795 | 9.46 | 4800 | 0.6203 | 0.6703 |
|
83 |
+
| 0.1768 | 10.25 | 5200 | 0.5645 | 0.6164 |
|
84 |
+
| 0.1637 | 11.03 | 5600 | 0.5804 | 0.6412 |
|
85 |
+
| 0.1573 | 11.82 | 6000 | 0.5914 | 0.5896 |
|
86 |
+
| 0.1467 | 12.61 | 6400 | 0.6517 | 0.6200 |
|
87 |
+
| 0.141 | 13.4 | 6800 | 0.6376 | 0.6310 |
|
88 |
+
| 0.135 | 14.19 | 7200 | 0.6343 | 0.6042 |
|
89 |
+
| 0.1279 | 14.98 | 7600 | 0.6680 | 0.6325 |
|
90 |
+
| 0.1222 | 15.76 | 8000 | 0.7109 | 0.6617 |
|
91 |
+
| 0.1169 | 16.55 | 8400 | 0.7067 | 0.6361 |
|
92 |
+
| 0.114 | 17.34 | 8800 | 0.7143 | 0.6144 |
|
93 |
+
| 0.1085 | 18.13 | 9200 | 0.6871 | 0.6081 |
|
94 |
+
| 0.0996 | 18.92 | 9600 | 0.8332 | 0.6569 |
|
95 |
+
| 0.0952 | 19.7 | 10000 | 0.7076 | 0.5992 |
|
96 |
+
| 0.0929 | 20.49 | 10400 | 0.6946 | 0.6078 |
|
97 |
+
| 0.0871 | 21.28 | 10800 | 0.6197 | 0.5822 |
|
98 |
+
| 0.0823 | 22.07 | 11200 | 0.6969 | 0.5876 |
|
99 |
+
| 0.0776 | 22.86 | 11600 | 0.6285 | 0.5619 |
|
100 |
+
| 0.0758 | 23.65 | 12000 | 0.7098 | 0.6010 |
|
101 |
+
| 0.0728 | 24.43 | 12400 | 0.6618 | 0.5905 |
|
102 |
+
| 0.0664 | 25.22 | 12800 | 0.6484 | 0.5536 |
|
103 |
+
| 0.0656 | 26.01 | 13200 | 0.6417 | 0.5593 |
|
104 |
+
| 0.0603 | 26.8 | 13600 | 0.7287 | 0.5813 |
|
105 |
+
| 0.0571 | 27.59 | 14000 | 0.6727 | 0.5700 |
|
106 |
+
| 0.0559 | 28.37 | 14400 | 0.6775 | 0.5631 |
|
107 |
+
| 0.0555 | 29.16 | 14800 | 0.7849 | 0.5968 |
|
108 |
+
| 0.0506 | 29.95 | 15200 | 0.8266 | 0.6185 |
|
109 |
+
| 0.0485 | 30.74 | 15600 | 0.7347 | 0.5747 |
|
110 |
+
| 0.0461 | 31.53 | 16000 | 0.6836 | 0.5432 |
|
111 |
+
| 0.0423 | 32.32 | 16400 | 0.6913 | 0.5396 |
|
112 |
+
| 0.0407 | 33.1 | 16800 | 0.6655 | 0.5328 |
|
113 |
+
| 0.04 | 33.89 | 17200 | 0.6873 | 0.5399 |
|
114 |
+
| 0.0396 | 34.68 | 17600 | 0.6822 | 0.5432 |
|
115 |
+
|
116 |
+
|
117 |
+
### Framework versions
|
118 |
+
|
119 |
+
- Transformers 4.35.0
|
120 |
+
- Pytorch 2.0.1+cu118
|
121 |
+
- Datasets 2.14.6
|
122 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262041132
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a4a9d4c2737359b4a8a60bf8a07ae021b55ff10a2eb6b78e3359f051bd802f
|
3 |
size 1262041132
|
runs/Nov02_18-53-57_38d2530731df/events.out.tfevents.1698951552.38d2530731df.355.0
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:ca935776b14bd7cfee34fb87f374890ea9f4f7f4e605afd958551c961e529248
|
3 |
+
size 27001
|