Hugging Face's logo

herwoww
/
mms-MGB2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
herwoww commited on
Commit
32b761e
•
1 Parent(s): 32ff496

Model save

Browse files
Files changed (3) hide show
  1. README.md +100 -0
  2. adapter.ara.safetensors +3 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-1b-all
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: mms-MGB2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # mms-MGB2
17
+
18
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: nan
21
+ - Wer: 1.0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 14
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: constant_with_warmup
46
+ - lr_scheduler_warmup_steps: 50
47
+ - training_steps: 10000
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 6.8035 | 0.01 | 250 | 5.9077 | 1.0036 |
54
+ | 2.2196 | 0.02 | 500 | 2.0224 | 0.9764 |
55
+ | 1.0641 | 0.03 | 750 | 0.8949 | 0.4840 |
56
+ | 0.8089 | 0.04 | 1000 | 0.7188 | 0.4095 |
57
+ | 1.7071 | 0.05 | 1250 | 0.7008 | 0.3974 |
58
+ | 0.8132 | 0.06 | 1500 | 0.6975 | 0.3986 |
59
+ | 0.9741 | 0.07 | 1750 | 0.6975 | 0.3986 |
60
+ | 0.8332 | 0.08 | 2000 | 0.6975 | 0.3986 |
61
+ | 0.8908 | 0.09 | 2250 | 0.6975 | 0.3986 |
62
+ | 0.8321 | 0.1 | 2500 | 0.6975 | 0.3986 |
63
+ | 0.7957 | 0.1 | 2750 | 0.6975 | 0.3986 |
64
+ | 0.9173 | 0.11 | 3000 | 0.6975 | 0.3986 |
65
+ | 2.0065 | 0.12 | 3250 | 0.6975 | 0.3986 |
66
+ | 0.8618 | 0.13 | 3500 | 0.6975 | 0.3986 |
67
+ | 0.9001 | 0.14 | 3750 | 0.6975 | 0.3986 |
68
+ | 1.0321 | 0.15 | 4000 | 0.6975 | 0.3986 |
69
+ | 0.8408 | 0.16 | 4250 | 0.6975 | 0.3986 |
70
+ | 0.8901 | 0.17 | 4500 | 0.6975 | 0.3986 |
71
+ | 0.8242 | 0.18 | 4750 | 0.6975 | 0.3986 |
72
+ | 0.8678 | 0.19 | 5000 | 0.6975 | 0.3986 |
73
+ | 0.8633 | 0.2 | 5250 | 0.6975 | 0.3986 |
74
+ | 0.8087 | 0.21 | 5500 | 0.6975 | 0.3986 |
75
+ | 0.9243 | 0.22 | 5750 | 0.6975 | 0.3986 |
76
+ | 0.7973 | 0.23 | 6000 | 0.6975 | 0.3986 |
77
+ | 0.835 | 0.24 | 6250 | 0.6975 | 0.3986 |
78
+ | 1.3251 | 0.25 | 6500 | 0.6975 | 0.3986 |
79
+ | 0.0 | 0.26 | 6750 | nan | 1.0 |
80
+ | 0.0 | 0.27 | 7000 | nan | 1.0 |
81
+ | 0.0 | 0.28 | 7250 | nan | 1.0 |
82
+ | 0.0 | 0.29 | 7500 | nan | 1.0 |
83
+ | 0.0 | 0.29 | 7750 | nan | 1.0 |
84
+ | 0.0 | 0.3 | 8000 | nan | 1.0 |
85
+ | 0.0 | 0.31 | 8250 | nan | 1.0 |
86
+ | 0.0 | 0.32 | 8500 | nan | 1.0 |
87
+ | 0.0 | 0.33 | 8750 | nan | 1.0 |
88
+ | 0.0 | 0.34 | 9000 | nan | 1.0 |
89
+ | 0.0 | 0.35 | 9250 | nan | 1.0 |
90
+ | 0.0 | 0.36 | 9500 | nan | 1.0 |
91
+ | 0.0 | 0.37 | 9750 | nan | 1.0 |
92
+ | 0.0 | 0.38 | 10000 | nan | 1.0 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.33.2
98
+ - Pytorch 2.0.1
99
+ - Datasets 2.19.1
100
+ - Tokenizers 0.13.3
adapter.ara.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4418197847bec4cf0cf9cf3ab65c31393e9b93bb2dcd557e20769669f96cadc
3
+ size 9075244
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e57690493001fbf6c9e1e118e80665d4cbdabec8be195668935a315de5ec8a65
3
  size 3859411277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84de2a2ac64d1688b45819c7552d3eaffa29a3300fe8fc285c28820131c878c
3
  size 3859411277