Hugging Face's logo

csikasote
/
mms-1b-all-bem-genbed-combined-adapter-test

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
genbed
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
bfe9d80
•
1 Parent(s): 1284371

Model save

Browse files
Files changed (2) hide show
  1. README.md +114 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: mms-1b-all-bem-genbed-combined-adapter-test
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
+ # mms-1b-all-bem-genbed-combined-adapter-test
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: 0.2294
22
+ - Wer: 0.3665
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0003
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 30.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 6.4783 | 0.1374 | 100 | 0.6403 | 0.69 |
56
+ | 0.5413 | 0.2747 | 200 | 0.3260 | 0.4931 |
57
+ | 0.437 | 0.4121 | 300 | 0.3014 | 0.4678 |
58
+ | 0.4402 | 0.5495 | 400 | 0.2982 | 0.4818 |
59
+ | 0.4153 | 0.6868 | 500 | 0.2936 | 0.4702 |
60
+ | 0.4154 | 0.8242 | 600 | 0.2884 | 0.4493 |
61
+ | 0.3789 | 0.9615 | 700 | 0.2806 | 0.4521 |
62
+ | 0.3667 | 1.0989 | 800 | 0.2764 | 0.4352 |
63
+ | 0.3929 | 1.2363 | 900 | 0.2763 | 0.4654 |
64
+ | 0.3847 | 1.3736 | 1000 | 0.2705 | 0.4406 |
65
+ | 0.3833 | 1.5110 | 1100 | 0.2697 | 0.4246 |
66
+ | 0.3742 | 1.6484 | 1200 | 0.2668 | 0.4250 |
67
+ | 0.3694 | 1.7857 | 1300 | 0.2690 | 0.4189 |
68
+ | 0.3494 | 1.9231 | 1400 | 0.2635 | 0.416 |
69
+ | 0.3724 | 2.0604 | 1500 | 0.2626 | 0.4323 |
70
+ | 0.3723 | 2.1978 | 1600 | 0.2598 | 0.4247 |
71
+ | 0.3505 | 2.3352 | 1700 | 0.2583 | 0.412 |
72
+ | 0.3393 | 2.4725 | 1800 | 0.2563 | 0.4128 |
73
+ | 0.3352 | 2.6099 | 1900 | 0.2545 | 0.4156 |
74
+ | 0.3516 | 2.7473 | 2000 | 0.2551 | 0.4315 |
75
+ | 0.3489 | 2.8846 | 2100 | 0.2560 | 0.4270 |
76
+ | 0.3512 | 3.0220 | 2200 | 0.2536 | 0.4039 |
77
+ | 0.339 | 3.1593 | 2300 | 0.2490 | 0.3989 |
78
+ | 0.3374 | 3.2967 | 2400 | 0.2495 | 0.3964 |
79
+ | 0.3295 | 3.4341 | 2500 | 0.2518 | 0.4037 |
80
+ | 0.3391 | 3.5714 | 2600 | 0.2491 | 0.4077 |
81
+ | 0.3373 | 3.7088 | 2700 | 0.2445 | 0.3989 |
82
+ | 0.3097 | 3.8462 | 2800 | 0.2462 | 0.4118 |
83
+ | 0.3458 | 3.9835 | 2900 | 0.2443 | 0.4034 |
84
+ | 0.313 | 4.1209 | 3000 | 0.2433 | 0.3882 |
85
+ | 0.3171 | 4.2582 | 3100 | 0.2426 | 0.3968 |
86
+ | 0.3122 | 4.3956 | 3200 | 0.2430 | 0.3936 |
87
+ | 0.3255 | 4.5330 | 3300 | 0.2404 | 0.3822 |
88
+ | 0.3253 | 4.6703 | 3400 | 0.2356 | 0.3946 |
89
+ | 0.3341 | 4.8077 | 3500 | 0.2369 | 0.3872 |
90
+ | 0.3183 | 4.9451 | 3600 | 0.2345 | 0.3854 |
91
+ | 0.3461 | 5.0824 | 3700 | 0.2395 | 0.3828 |
92
+ | 0.3147 | 5.2198 | 3800 | 0.2359 | 0.3775 |
93
+ | 0.317 | 5.3571 | 3900 | 0.2320 | 0.3808 |
94
+ | 0.3094 | 5.4945 | 4000 | 0.2366 | 0.3797 |
95
+ | 0.2913 | 5.6319 | 4100 | 0.2357 | 0.3749 |
96
+ | 0.3195 | 5.7692 | 4200 | 0.2332 | 0.3694 |
97
+ | 0.3189 | 5.9066 | 4300 | 0.2313 | 0.3870 |
98
+ | 0.3105 | 6.0440 | 4400 | 0.2326 | 0.3806 |
99
+ | 0.2937 | 6.1813 | 4500 | 0.2346 | 0.3784 |
100
+ | 0.3088 | 6.3187 | 4600 | 0.2313 | 0.3726 |
101
+ | 0.2852 | 6.4560 | 4700 | 0.2307 | 0.3709 |
102
+ | 0.3083 | 6.5934 | 4800 | 0.2293 | 0.3752 |
103
+ | 0.3194 | 6.7308 | 4900 | 0.2292 | 0.3711 |
104
+ | 0.297 | 6.8681 | 5000 | 0.2303 | 0.3715 |
105
+ | 0.3086 | 7.0055 | 5100 | 0.2340 | 0.4027 |
106
+ | 0.3058 | 7.1429 | 5200 | 0.2294 | 0.3665 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.46.0.dev0
112
+ - Pytorch 2.4.1+cu121
113
+ - Datasets 3.0.1
114
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:637444412b234ccf7161baebac3af7744b8e457c18f7b9475a44435d85cf3e82
3
  size 3858890924
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3931dbedd679badd74b2afd8e1dfcf522f35ecf932046281534f36fc82e271bf
3
  size 3858890924