End of training
Browse files- README.md +99 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: LugandaASRwav2Vec300M
|
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: lg
|
20 |
+
split: validation
|
21 |
+
args: lg
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.22313171042840438
|
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 |
+
# LugandaASRwav2Vec300M
|
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: 0.1741
|
36 |
+
- Wer: 0.2231
|
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: 4
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 24
|
60 |
+
- total_train_batch_size: 96
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_steps: 200
|
64 |
+
- num_epochs: 3
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 6.4394 | 0.14 | 100 | 2.9784 | 1.0 |
|
71 |
+
| 2.8739 | 0.27 | 200 | 2.7056 | 1.0000 |
|
72 |
+
| 1.2203 | 0.41 | 300 | 0.5656 | 0.7264 |
|
73 |
+
| 0.4507 | 0.54 | 400 | 0.3978 | 0.5258 |
|
74 |
+
| 0.3657 | 0.68 | 500 | 0.3314 | 0.4416 |
|
75 |
+
| 0.3131 | 0.81 | 600 | 0.2996 | 0.4049 |
|
76 |
+
| 0.2886 | 0.95 | 700 | 0.2823 | 0.3766 |
|
77 |
+
| 0.2535 | 1.08 | 800 | 0.2517 | 0.3317 |
|
78 |
+
| 0.2279 | 1.22 | 900 | 0.2407 | 0.3190 |
|
79 |
+
| 0.2209 | 1.36 | 1000 | 0.2296 | 0.3077 |
|
80 |
+
| 0.2075 | 1.49 | 1100 | 0.2228 | 0.2931 |
|
81 |
+
| 0.1983 | 1.63 | 1200 | 0.2139 | 0.2809 |
|
82 |
+
| 0.1902 | 1.76 | 1300 | 0.2093 | 0.2688 |
|
83 |
+
| 0.1931 | 1.9 | 1400 | 0.2019 | 0.2666 |
|
84 |
+
| 0.1741 | 2.03 | 1500 | 0.1951 | 0.2521 |
|
85 |
+
| 0.1481 | 2.17 | 1600 | 0.1934 | 0.2435 |
|
86 |
+
| 0.1423 | 2.3 | 1700 | 0.1912 | 0.2409 |
|
87 |
+
| 0.1413 | 2.44 | 1800 | 0.1841 | 0.2368 |
|
88 |
+
| 0.1361 | 2.58 | 1900 | 0.1813 | 0.2310 |
|
89 |
+
| 0.1337 | 2.71 | 2000 | 0.1775 | 0.2279 |
|
90 |
+
| 0.1358 | 2.85 | 2100 | 0.1756 | 0.2247 |
|
91 |
+
| 0.133 | 2.98 | 2200 | 0.1741 | 0.2231 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- Transformers 4.32.0
|
97 |
+
- Pytorch 2.0.1+cu118
|
98 |
+
- Datasets 2.13.0
|
99 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262028973
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb07a2b8cd5a7c467aaadcbac11a3a02aa49b570010058a4c66d17f2ac3fffc8
|
3 |
size 1262028973
|