End of training
Browse files
README.md
CHANGED
@@ -3,9 +3,26 @@ license: mit
|
|
3 |
base_model: facebook/w2v-bert-2.0
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: w2v-bert-2.0-swahili-V100-32GB-CV14.0
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# w2v-bert-2.0-swahili-V100-32GB-CV14.0
|
15 |
|
16 |
-
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,6 +65,45 @@ The following hyperparameters were used during training:
|
|
44 |
- training_steps: 10000
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
- Transformers 4.38.1
|
|
|
3 |
base_model: facebook/w2v-bert-2.0
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice_14_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
model-index:
|
11 |
- name: w2v-bert-2.0-swahili-V100-32GB-CV14.0
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice_14_0
|
18 |
+
type: common_voice_14_0
|
19 |
+
config: sw
|
20 |
+
split: test
|
21 |
+
args: sw
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.9282208525831644
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# w2v-bert-2.0-swahili-V100-32GB-CV14.0
|
32 |
|
33 |
+
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_14_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: inf
|
36 |
+
- Wer: 0.9282
|
37 |
+
- Cer: 0.3257
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
65 |
- training_steps: 10000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
72 |
+
| 1.5245 | 0.19 | 300 | inf | 0.2379 | 0.0709 |
|
73 |
+
| 0.2545 | 0.38 | 600 | inf | 0.2225 | 0.0672 |
|
74 |
+
| 0.2269 | 0.57 | 900 | inf | 0.2020 | 0.0621 |
|
75 |
+
| 0.2027 | 0.77 | 1200 | inf | 0.1941 | 0.0604 |
|
76 |
+
| 0.1866 | 0.96 | 1500 | inf | 0.1893 | 0.0591 |
|
77 |
+
| 0.1721 | 1.15 | 1800 | inf | 0.1747 | 0.0538 |
|
78 |
+
| 0.1689 | 1.34 | 2100 | inf | 0.1781 | 0.0543 |
|
79 |
+
| 0.1647 | 1.53 | 2400 | inf | 0.1795 | 0.0545 |
|
80 |
+
| 0.1652 | 1.72 | 2700 | inf | 0.1736 | 0.0541 |
|
81 |
+
| 0.1659 | 1.91 | 3000 | inf | 0.1733 | 0.0528 |
|
82 |
+
| 0.1653 | 2.1 | 3300 | inf | 0.1753 | 0.0532 |
|
83 |
+
| 0.1577 | 2.3 | 3600 | inf | 0.1762 | 0.0530 |
|
84 |
+
| 0.192 | 2.49 | 3900 | inf | 0.1876 | 0.0579 |
|
85 |
+
| 0.2557 | 2.68 | 4200 | inf | 0.2411 | 0.0619 |
|
86 |
+
| 0.3876 | 2.87 | 4500 | inf | 0.2376 | 0.0677 |
|
87 |
+
| 0.4498 | 3.06 | 4800 | inf | 0.2080 | 0.0622 |
|
88 |
+
| 0.4865 | 3.25 | 5100 | inf | 0.2706 | 0.0744 |
|
89 |
+
| 0.842 | 3.44 | 5400 | inf | 0.5120 | 0.1169 |
|
90 |
+
| 0.9809 | 3.64 | 5700 | inf | 0.6735 | 0.1610 |
|
91 |
+
| 1.0493 | 3.83 | 6000 | inf | 0.8517 | 0.2787 |
|
92 |
+
| 1.236 | 4.02 | 6300 | inf | 0.7717 | 0.1951 |
|
93 |
+
| 1.2051 | 4.21 | 6600 | inf | 0.7491 | 0.1868 |
|
94 |
+
| 1.1908 | 4.4 | 6900 | inf | 0.8410 | 0.2340 |
|
95 |
+
| 1.1987 | 4.59 | 7200 | inf | 0.9118 | 0.2833 |
|
96 |
+
| 1.2397 | 4.78 | 7500 | inf | 0.9282 | 0.3257 |
|
97 |
+
| 1.2443 | 4.97 | 7800 | inf | 0.9282 | 0.3257 |
|
98 |
+
| 1.2428 | 5.17 | 8100 | inf | 0.9282 | 0.3257 |
|
99 |
+
| 1.2422 | 5.36 | 8400 | inf | 0.9282 | 0.3257 |
|
100 |
+
| 1.249 | 5.55 | 8700 | inf | 0.9282 | 0.3257 |
|
101 |
+
| 1.2518 | 5.74 | 9000 | inf | 0.9282 | 0.3257 |
|
102 |
+
| 1.2374 | 5.93 | 9300 | inf | 0.9282 | 0.3257 |
|
103 |
+
| 1.2369 | 6.12 | 9600 | inf | 0.9282 | 0.3257 |
|
104 |
+
| 1.2454 | 6.31 | 9900 | inf | 0.9282 | 0.3257 |
|
105 |
+
|
106 |
+
|
107 |
### Framework versions
|
108 |
|
109 |
- Transformers 4.38.1
|