Hugging Face's logo

hilaltekgoz
/
model_mms

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hilaltekgoz commited on
Commit
bc57c96
•
1 Parent(s): 56f6db2

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -12
  2. model.safetensors +1 -1
  3. runs/Jan11_12-43-35_76f6f48fe926/events.out.tfevents.1704977661.76f6f48fe926.1646.2 +2 -2
README.md CHANGED
@@ -17,12 +17,12 @@ model-index:
17
  name: common_voice_11_0
18
  type: common_voice_11_0
19
  config: tr
20
- split: test[:10]
21
  args: tr
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.44285714285714284
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_11_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4310
36
- - Wer: 0.4429
37
 
38
  ## Model description
39
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:------:|
69
- | 0.2499 | 0.12 | 100 | 0.4539 | 0.4714 |
70
- | 0.2405 | 0.25 | 200 | 0.4487 | 0.4429 |
71
- | 0.235 | 0.37 | 300 | 0.4289 | 0.4143 |
72
- | 0.2432 | 0.49 | 400 | 0.4239 | 0.4 |
73
- | 0.2373 | 0.61 | 500 | 0.4380 | 0.4429 |
74
- | 0.2341 | 0.74 | 600 | 0.4435 | 0.4286 |
75
- | 0.2333 | 0.86 | 700 | 0.4459 | 0.4429 |
76
- | 0.2348 | 0.98 | 800 | 0.4310 | 0.4429 |
77
 
78
 
79
  ### Framework versions
 
17
  name: common_voice_11_0
18
  type: common_voice_11_0
19
  config: tr
20
+ split: test[:100]
21
  args: tr
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.3283018867924528
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_11_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2666
36
+ - Wer: 0.3283
37
 
38
  ## Model description
39
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 3.0741 | 0.12 | 100 | 0.3252 | 0.3698 |
70
+ | 0.2837 | 0.24 | 200 | 0.2980 | 0.3509 |
71
+ | 0.2725 | 0.36 | 300 | 0.2808 | 0.3566 |
72
+ | 0.2727 | 0.47 | 400 | 0.2893 | 0.3509 |
73
+ | 0.2721 | 0.59 | 500 | 0.2806 | 0.3377 |
74
+ | 0.2602 | 0.71 | 600 | 0.2832 | 0.3377 |
75
+ | 0.2631 | 0.83 | 700 | 0.2740 | 0.3396 |
76
+ | 0.2528 | 0.95 | 800 | 0.2666 | 0.3283 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6cfae0c69cb23134f783e7f13c36c9dd32081deed5dd2f4ef24d74ab7e78c63
3
  size 3858942164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9263ff74d27ff63117dd1f740bed37245d33bf99e9ae070c586752f34932e27
3
  size 3858942164
runs/Jan11_12-43-35_76f6f48fe926/events.out.tfevents.1704977661.76f6f48fe926.1646.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32d385bc40c47d5410550757471255f9045c440d0d7adf9cb67ab6cf4101a4e8
3
- size 8641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8329a06c0940c5691d115e9b1981165ed3e91962ab6f1a134061c9ac14360ec3
3
+ size 9945