franziskaM
commited on
Commit
•
05c4690
1
Parent(s):
2041977
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice_13_0
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: b20-wav2vec2-large-xls-r-romansh-colab
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: common_voice_13_0
|
17 |
+
type: common_voice_13_0
|
18 |
+
config: rm-vallader
|
19 |
+
split: test
|
20 |
+
args: rm-vallader
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 0.31811830461108526
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# b20-wav2vec2-large-xls-r-romansh-colab
|
31 |
+
|
32 |
+
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.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3738
|
35 |
+
- Wer: 0.3181
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0001
|
55 |
+
- train_batch_size: 4
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 2
|
59 |
+
- total_train_batch_size: 8
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 100
|
63 |
+
- num_epochs: 30
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 9.6653 | 0.76 | 100 | 3.2423 | 1.0 |
|
71 |
+
| 3.0224 | 1.52 | 200 | 3.0321 | 1.0 |
|
72 |
+
| 2.969 | 2.29 | 300 | 3.0174 | 1.0 |
|
73 |
+
| 2.964 | 3.05 | 400 | 2.9531 | 1.0 |
|
74 |
+
| 2.9488 | 3.81 | 500 | 2.9441 | 1.0 |
|
75 |
+
| 2.962 | 4.58 | 600 | 2.9383 | 1.0 |
|
76 |
+
| 2.9646 | 5.34 | 700 | 2.9377 | 1.0 |
|
77 |
+
| 2.9411 | 6.11 | 800 | 2.9303 | 1.0 |
|
78 |
+
| 2.9313 | 6.87 | 900 | 2.9264 | 1.0 |
|
79 |
+
| 2.9327 | 7.63 | 1000 | 2.9211 | 1.0 |
|
80 |
+
| 2.9574 | 8.4 | 1100 | 2.9145 | 1.0 |
|
81 |
+
| 2.9227 | 9.16 | 1200 | 2.9034 | 1.0 |
|
82 |
+
| 2.8916 | 9.92 | 1300 | 2.8764 | 1.0 |
|
83 |
+
| 2.8311 | 10.68 | 1400 | 2.5611 | 0.9995 |
|
84 |
+
| 2.0497 | 11.45 | 1500 | 1.1256 | 0.8784 |
|
85 |
+
| 1.2359 | 12.21 | 1600 | 0.7668 | 0.7143 |
|
86 |
+
| 0.9607 | 12.97 | 1700 | 0.6340 | 0.6388 |
|
87 |
+
| 0.804 | 13.74 | 1800 | 0.5658 | 0.5806 |
|
88 |
+
| 0.693 | 14.5 | 1900 | 0.5147 | 0.5389 |
|
89 |
+
| 0.6403 | 15.27 | 2000 | 0.4711 | 0.4797 |
|
90 |
+
| 0.5716 | 16.03 | 2100 | 0.4298 | 0.4520 |
|
91 |
+
| 0.5124 | 16.79 | 2200 | 0.4353 | 0.4313 |
|
92 |
+
| 0.5104 | 17.56 | 2300 | 0.3991 | 0.3952 |
|
93 |
+
| 0.4416 | 18.32 | 2400 | 0.4012 | 0.3933 |
|
94 |
+
| 0.4419 | 19.08 | 2500 | 0.3945 | 0.3687 |
|
95 |
+
| 0.406 | 19.84 | 2600 | 0.4003 | 0.3675 |
|
96 |
+
| 0.3946 | 20.61 | 2700 | 0.3901 | 0.3579 |
|
97 |
+
| 0.379 | 21.37 | 2800 | 0.3963 | 0.3537 |
|
98 |
+
| 0.3663 | 22.14 | 2900 | 0.3826 | 0.3435 |
|
99 |
+
| 0.3425 | 22.9 | 3000 | 0.3850 | 0.3435 |
|
100 |
+
| 0.3396 | 23.66 | 3100 | 0.3852 | 0.3405 |
|
101 |
+
| 0.3041 | 24.43 | 3200 | 0.3771 | 0.3265 |
|
102 |
+
| 0.3194 | 25.19 | 3300 | 0.3796 | 0.3265 |
|
103 |
+
| 0.312 | 25.95 | 3400 | 0.3734 | 0.3228 |
|
104 |
+
| 0.313 | 26.71 | 3500 | 0.3864 | 0.3270 |
|
105 |
+
| 0.3039 | 27.48 | 3600 | 0.3734 | 0.3149 |
|
106 |
+
| 0.2929 | 28.24 | 3700 | 0.3785 | 0.3223 |
|
107 |
+
| 0.2884 | 29.01 | 3800 | 0.3734 | 0.3160 |
|
108 |
+
| 0.2812 | 29.77 | 3900 | 0.3738 | 0.3181 |
|
109 |
+
|
110 |
+
|
111 |
+
### Framework versions
|
112 |
+
|
113 |
+
- Transformers 4.26.0
|
114 |
+
- Pytorch 2.0.1+cu118
|
115 |
+
- Datasets 2.14.4
|
116 |
+
- Tokenizers 0.13.3
|