Hugging Face's logo

simpragma
/
breeze-listen-w2v2-id

Automatic Speech Recognition
Transformers
Safetensors
Indonesian
wav2vec2
mozilla-foundation/common_voice_16_0
mms
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hanasim commited on
Commit
ebcc9ce
•
1 Parent(s): e37a63a

Model save

Browse files
Files changed (2) hide show
  1. README.md +118 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - common_voice_16_0
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: breeze-listen-w2v2-id
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_16_0
18
+ type: common_voice_16_0
19
+ config: id
20
+ split: test
21
+ args: id
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.1455760839290688
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
+ # breeze-listen-w2v2-id
32
+
33
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_16_0 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.1253
36
+ - Wer: 0.1456
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: 0.001
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - distributed_type: multi-GPU
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: 4.0
64
+ - mixed_precision_training: Native AMP
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | No log | 0.1 | 200 | 3.2671 | 1.0 |
71
+ | No log | 0.19 | 400 | 2.8741 | 1.0007 |
72
+ | 3.8381 | 0.29 | 600 | 2.7612 | 0.9955 |
73
+ | 3.8381 | 0.38 | 800 | 2.6333 | 0.9981 |
74
+ | 2.6996 | 0.48 | 1000 | 2.3074 | 0.9771 |
75
+ | 2.6996 | 0.58 | 1200 | 2.0155 | 0.9286 |
76
+ | 2.6996 | 0.67 | 1400 | 1.9155 | 0.8947 |
77
+ | 2.2919 | 0.77 | 1600 | 1.6412 | 0.8814 |
78
+ | 2.2919 | 0.87 | 1800 | 1.4531 | 0.8285 |
79
+ | 1.5872 | 0.96 | 2000 | 0.1813 | 0.2060 |
80
+ | 1.5872 | 1.06 | 2200 | 0.1636 | 0.1806 |
81
+ | 1.5872 | 1.15 | 2400 | 0.1558 | 0.1744 |
82
+ | 0.2659 | 1.25 | 2600 | 0.1522 | 0.1647 |
83
+ | 0.2659 | 1.35 | 2800 | 0.1553 | 0.1664 |
84
+ | 0.2436 | 1.44 | 3000 | 0.1841 | 0.1961 |
85
+ | 0.2436 | 1.54 | 3200 | 0.1419 | 0.1640 |
86
+ | 0.2436 | 1.64 | 3400 | 0.1456 | 0.1714 |
87
+ | 0.2464 | 1.73 | 3600 | 0.1402 | 0.1607 |
88
+ | 0.2464 | 1.83 | 3800 | 0.1345 | 0.1528 |
89
+ | 0.2292 | 1.92 | 4000 | 0.1342 | 0.1556 |
90
+ | 0.2292 | 2.02 | 4200 | 0.1334 | 0.1552 |
91
+ | 0.2292 | 2.12 | 4400 | 0.1352 | 0.1543 |
92
+ | 0.2209 | 2.21 | 4600 | 0.1350 | 0.1538 |
93
+ | 0.2209 | 2.31 | 4800 | 0.1342 | 0.1530 |
94
+ | 0.2136 | 2.41 | 5000 | 0.1320 | 0.1540 |
95
+ | 0.2136 | 2.5 | 5200 | 0.1369 | 0.1569 |
96
+ | 0.2136 | 2.6 | 5400 | 0.1314 | 0.1517 |
97
+ | 0.2154 | 2.69 | 5600 | 0.1304 | 0.1506 |
98
+ | 0.2154 | 2.79 | 5800 | 0.1320 | 0.1507 |
99
+ | 0.2123 | 2.89 | 6000 | 0.1319 | 0.1524 |
100
+ | 0.2123 | 2.98 | 6200 | 0.1292 | 0.1524 |
101
+ | 0.2123 | 3.08 | 6400 | 0.1283 | 0.1488 |
102
+ | 0.2109 | 3.18 | 6600 | 0.1258 | 0.1492 |
103
+ | 0.2109 | 3.27 | 6800 | 0.1291 | 0.1488 |
104
+ | 0.2103 | 3.37 | 7000 | 0.1278 | 0.1484 |
105
+ | 0.2103 | 3.46 | 7200 | 0.1250 | 0.1478 |
106
+ | 0.2103 | 3.56 | 7400 | 0.1277 | 0.1482 |
107
+ | 0.1986 | 3.66 | 7600 | 0.1256 | 0.1476 |
108
+ | 0.1986 | 3.75 | 7800 | 0.1258 | 0.1468 |
109
+ | 0.1954 | 3.85 | 8000 | 0.1256 | 0.1465 |
110
+ | 0.1954 | 3.95 | 8200 | 0.1253 | 0.1456 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.38.0.dev0
116
+ - Pytorch 2.1.2+cu121
117
+ - Datasets 2.16.1
118
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba10a21f0c777fc07e2cbb133d6f4a3044a9ebd280777ef5fe7fefb106cc86cd
3
  size 3858952412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08e3f1b083d132524d020779b6328be2e31d6857f3065b489fa12da5391d3a2
3
  size 3858952412