Hugging Face's logo

csikasote
/
mms-zeroshot-300m-bembaspeech-model

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
BembaSpeech
mms
Generated from Trainer
Inference Endpoints
Model card Files Community
csikasote commited on
Commit
7e849c3
·
verified ·
1 Parent(s): 5442855

Model save

Browse files
Files changed (2) hide show
  1. README.md +88 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: mms-meta/mms-zeroshot-300m
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: mms-zeroshot-300m-bembaspeech-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
+ # mms-zeroshot-300m-bembaspeech-model
18
+
19
+ This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2050
22
+ - Wer: 0.3964
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
+ | No log | 0.1405 | 200 | 2.2803 | 1.0 |
56
+ | No log | 0.2811 | 400 | 0.2945 | 0.5101 |
57
+ | 2.741 | 0.4216 | 600 | 0.2641 | 0.4834 |
58
+ | 2.741 | 0.5622 | 800 | 0.2611 | 0.4743 |
59
+ | 0.5962 | 0.7027 | 1000 | 0.2608 | 0.4831 |
60
+ | 0.5962 | 0.8433 | 1200 | 0.2477 | 0.4563 |
61
+ | 0.5962 | 0.9838 | 1400 | 0.2407 | 0.4567 |
62
+ | 0.536 | 1.1244 | 1600 | 0.2343 | 0.4412 |
63
+ | 0.536 | 1.2649 | 1800 | 0.2307 | 0.4423 |
64
+ | 0.5221 | 1.4055 | 2000 | 0.2252 | 0.4348 |
65
+ | 0.5221 | 1.5460 | 2200 | 0.2228 | 0.4326 |
66
+ | 0.5221 | 1.6866 | 2400 | 0.2162 | 0.4253 |
67
+ | 0.5027 | 1.8271 | 2600 | 0.2200 | 0.4188 |
68
+ | 0.5027 | 1.9677 | 2800 | 0.2131 | 0.4142 |
69
+ | 0.4818 | 2.1082 | 3000 | 0.2281 | 0.4281 |
70
+ | 0.4818 | 2.2488 | 3200 | 0.2178 | 0.4147 |
71
+ | 0.4818 | 2.3893 | 3400 | 0.2123 | 0.4155 |
72
+ | 0.4619 | 2.5299 | 3600 | 0.2142 | 0.4079 |
73
+ | 0.4619 | 2.6704 | 3800 | 0.2156 | 0.4011 |
74
+ | 0.464 | 2.8110 | 4000 | 0.2072 | 0.4009 |
75
+ | 0.464 | 2.9515 | 4200 | 0.2128 | 0.4013 |
76
+ | 0.464 | 3.0921 | 4400 | 0.2056 | 0.3982 |
77
+ | 0.4464 | 3.2326 | 4600 | 0.2038 | 0.4007 |
78
+ | 0.4464 | 3.3732 | 4800 | 0.2089 | 0.3987 |
79
+ | 0.4418 | 3.5137 | 5000 | 0.2043 | 0.4009 |
80
+ | 0.4418 | 3.6543 | 5200 | 0.2050 | 0.3964 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.46.0.dev0
86
+ - Pytorch 2.4.1+cu121
87
+ - Datasets 3.0.1
88
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28fc6e76cfd2c0e072ab91da906d70b328e3d0efc6c45a61106cfe08c1f98f4e
3
  size 1265394748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063bda10b23f395b7a1a27a7e439862237d38adac5421e9a02c884a4db00872c
3
  size 1265394748