Hugging Face's logo

ctaguchi
/
ssc-bew-mms-model

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
ctaguchi commited on
Commit
2d49878
·
verified ·
1 Parent(s): 847d0b1

Model save

Browse files
Files changed (2) hide show
  1. README.md +97 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/mms-1b-all
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: ssc-bew-mms-model
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # ssc-bew-mms-model
18
+
19
+ This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7747
22
+ - Cer: 0.2038
23
+ - Wer: 0.6111
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0003
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 12
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 16
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 100
51
+ - num_epochs: 10
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
57
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
58
+ | 1.6619 | 0.3063 | 200 | 0.9694 | 0.2219 | 0.6669 |
59
+ | 1.5435 | 0.6126 | 400 | 0.8620 | 0.2158 | 0.6542 |
60
+ | 1.5126 | 0.9188 | 600 | 0.8212 | 0.2101 | 0.6326 |
61
+ | 1.4544 | 1.2251 | 800 | 0.8192 | 0.2101 | 0.6346 |
62
+ | 1.4753 | 1.5314 | 1000 | 0.8128 | 0.2096 | 0.6393 |
63
+ | 1.4388 | 1.8377 | 1200 | 0.8112 | 0.2098 | 0.6292 |
64
+ | 1.4494 | 2.1440 | 1400 | 0.8120 | 0.2084 | 0.6268 |
65
+ | 1.4289 | 2.4502 | 1600 | 0.7985 | 0.2075 | 0.6254 |
66
+ | 1.4736 | 2.7565 | 1800 | 0.7951 | 0.2070 | 0.6263 |
67
+ | 1.4217 | 3.0628 | 2000 | 0.8154 | 0.2104 | 0.6369 |
68
+ | 1.4146 | 3.3691 | 2200 | 0.8092 | 0.2094 | 0.6295 |
69
+ | 1.4205 | 3.6753 | 2400 | 0.8056 | 0.2092 | 0.6298 |
70
+ | 1.3951 | 3.9816 | 2600 | 0.8070 | 0.2087 | 0.6384 |
71
+ | 1.3695 | 4.2879 | 2800 | 0.7980 | 0.2078 | 0.6261 |
72
+ | 1.4743 | 4.5942 | 3000 | 0.8138 | 0.2099 | 0.6376 |
73
+ | 1.4499 | 4.9005 | 3200 | 0.7828 | 0.2041 | 0.6168 |
74
+ | 1.3801 | 5.2067 | 3400 | 0.8019 | 0.2086 | 0.6324 |
75
+ | 1.4191 | 5.5130 | 3600 | 0.7931 | 0.2064 | 0.6229 |
76
+ | 1.4359 | 5.8193 | 3800 | 0.7794 | 0.2034 | 0.6144 |
77
+ | 1.407 | 6.1256 | 4000 | 0.7877 | 0.2064 | 0.6243 |
78
+ | 1.4079 | 6.4319 | 4200 | 0.7963 | 0.2071 | 0.6221 |
79
+ | 1.417 | 6.7381 | 4400 | 0.7839 | 0.2048 | 0.6139 |
80
+ | 1.4031 | 7.0444 | 4600 | 0.7759 | 0.2033 | 0.6098 |
81
+ | 1.3999 | 7.3507 | 4800 | 0.7781 | 0.2043 | 0.6137 |
82
+ | 1.4052 | 7.6570 | 5000 | 0.7769 | 0.2041 | 0.6110 |
83
+ | 1.4102 | 7.9632 | 5200 | 0.7750 | 0.2031 | 0.6085 |
84
+ | 1.392 | 8.2695 | 5400 | 0.7776 | 0.2041 | 0.6115 |
85
+ | 1.4032 | 8.5758 | 5600 | 0.7733 | 0.2033 | 0.6096 |
86
+ | 1.3956 | 8.8821 | 5800 | 0.7761 | 0.2038 | 0.6101 |
87
+ | 1.4148 | 9.1884 | 6000 | 0.7761 | 0.2040 | 0.6102 |
88
+ | 1.3921 | 9.4946 | 6200 | 0.7746 | 0.2036 | 0.6099 |
89
+ | 1.4109 | 9.8009 | 6400 | 0.7747 | 0.2038 | 0.6111 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.57.2
95
+ - Pytorch 2.9.1+cu128
96
+ - Datasets 3.6.0
97
+ - Tokenizers 0.22.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38a77f129db06027bfbc1bd4980d40304fd20896356400ffe104401dead8893b
3
  size 3859142000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74934ed45cb31dfa485f6cd41075256a0905aff2b36021d5719afc02121dfcaf
3
  size 3859142000