dmusingu commited on
Commit
b5af4b4
·
verified ·
1 Parent(s): f2094b2

asr-africa/bambara-mms-1-hour-jeli-asr-hf

Browse files
Files changed (2) hide show
  1. README.md +18 -0
  2. model.safetensors +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: cc-by-nc-4.0
4
  base_model: facebook/mms-1b-all
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: bambara-mms-1-hour-jeli-asr-hf
9
  results: []
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
16
  # bambara-mms-1-hour-jeli-asr-hf
17
 
18
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
 
 
 
 
19
 
20
  ## Model description
21
 
@@ -45,6 +51,18 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_warmup_steps: 500
46
  - num_epochs: 50
47
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.45.1
 
4
  base_model: facebook/mms-1b-all
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: bambara-mms-1-hour-jeli-asr-hf
11
  results: []
 
18
  # bambara-mms-1-hour-jeli-asr-hf
19
 
20
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 3.3954
23
+ - Wer: 0.7301
24
+ - Cer: 0.3627
25
 
26
  ## Model description
27
 
 
51
  - lr_scheduler_warmup_steps: 500
52
  - num_epochs: 50
53
 
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
57
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
58
+ | 1.6441 | 8.0 | 500 | 1.6965 | 0.7606 | 0.3865 |
59
+ | 0.9143 | 16.0 | 1000 | 2.0093 | 0.7460 | 0.3704 |
60
+ | 0.5249 | 24.0 | 1500 | 2.2733 | 0.7912 | 0.3808 |
61
+ | 0.3111 | 32.0 | 2000 | 2.7380 | 0.7231 | 0.3678 |
62
+ | 0.1826 | 40.0 | 2500 | 3.0810 | 0.7323 | 0.3626 |
63
+ | 0.1135 | 48.0 | 3000 | 3.3954 | 0.7301 | 0.3627 |
64
+
65
+
66
  ### Framework versions
67
 
68
  - Transformers 4.45.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64b3340c24697fe65b7d87dd1efc99ce146d600c0cdccaabbe92996f89cd0089
3
  size 3858921668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256673ed25a536ea0e51344a0c2bc4b6fa9120eac0247f293bfbf9f2ebfb8841
3
  size 3858921668