Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-cy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
f0d36e2
•
1 Parent(s): a8f098a

Model save

Browse files
Files changed (3) hide show
  1. README.md +29 -31
  2. model.safetensors +1 -1
  3. runs/May17_07-56-01_2e698a9c250f/events.out.tfevents.1715929316.2e698a9c250f.3965.0 +2 -2
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
- - automatic-speech-recognition
6
- - DewiBrynJones/banc-trawsgrifiadau-bangor-normalized
7
  - generated_from_trainer
8
  metrics:
9
  - wer
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # wav2vec2-xlsr-53-ft-btb-cy
19
 
20
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-NORMALIZED - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4105
23
- - Wer: 0.3136
24
 
25
  ## Model description
26
 
@@ -55,32 +53,32 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:------:|
58
- | No log | 0.1414 | 100 | 3.2195 | 1.0 |
59
- | No log | 0.2829 | 200 | 3.1180 | 1.0 |
60
- | No log | 0.4243 | 300 | 1.7236 | 0.9364 |
61
- | No log | 0.5658 | 400 | 1.1579 | 0.7628 |
62
- | 3.0279 | 0.7072 | 500 | 0.9558 | 0.6721 |
63
- | 3.0279 | 0.8487 | 600 | 0.8189 | 0.6424 |
64
- | 3.0279 | 0.9901 | 700 | 0.6973 | 0.5164 |
65
- | 3.0279 | 1.1315 | 800 | 0.6183 | 0.4752 |
66
- | 3.0279 | 1.2730 | 900 | 0.5936 | 0.4703 |
67
- | 0.7925 | 1.4144 | 1000 | 0.5498 | 0.4304 |
68
- | 0.7925 | 1.5559 | 1100 | 0.5286 | 0.4148 |
69
- | 0.7925 | 1.6973 | 1200 | 0.5130 | 0.3974 |
70
- | 0.7925 | 1.8388 | 1300 | 0.4878 | 0.3864 |
71
- | 0.7925 | 1.9802 | 1400 | 0.4740 | 0.3733 |
72
- | 0.62 | 2.1216 | 1500 | 0.4578 | 0.3593 |
73
- | 0.62 | 2.2631 | 1600 | 0.4535 | 0.3500 |
74
- | 0.62 | 2.4045 | 1700 | 0.4485 | 0.3497 |
75
- | 0.62 | 2.5460 | 1800 | 0.4373 | 0.3431 |
76
- | 0.62 | 2.6874 | 1900 | 0.4362 | 0.3429 |
77
- | 0.4879 | 2.8289 | 2000 | 0.4236 | 0.3327 |
78
- | 0.4879 | 2.9703 | 2100 | 0.4172 | 0.3257 |
79
- | 0.4879 | 3.1117 | 2200 | 0.4206 | 0.3217 |
80
- | 0.4879 | 3.2532 | 2300 | 0.4166 | 0.3199 |
81
- | 0.4879 | 3.3946 | 2400 | 0.4134 | 0.3173 |
82
- | 0.4036 | 3.5361 | 2500 | 0.4110 | 0.3159 |
83
- | 0.4036 | 3.6775 | 2600 | 0.4105 | 0.3136 |
84
 
85
 
86
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
15
 
16
  # wav2vec2-xlsr-53-ft-btb-cy
17
 
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4159
21
+ - Wer: 0.3171
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|
56
+ | No log | 0.1414 | 100 | 3.4000 | 1.0 |
57
+ | No log | 0.2829 | 200 | 2.9513 | 1.0 |
58
+ | No log | 0.4243 | 300 | 1.9454 | 0.9325 |
59
+ | No log | 0.5658 | 400 | 1.1412 | 0.7730 |
60
+ | 3.2243 | 0.7072 | 500 | 0.9250 | 0.6789 |
61
+ | 3.2243 | 0.8487 | 600 | 0.8018 | 0.5983 |
62
+ | 3.2243 | 0.9901 | 700 | 0.7182 | 0.5409 |
63
+ | 3.2243 | 1.1315 | 800 | 0.6198 | 0.4770 |
64
+ | 3.2243 | 1.2730 | 900 | 0.6102 | 0.4712 |
65
+ | 0.7983 | 1.4144 | 1000 | 0.5605 | 0.4426 |
66
+ | 0.7983 | 1.5559 | 1100 | 0.5336 | 0.4162 |
67
+ | 0.7983 | 1.6973 | 1200 | 0.5259 | 0.4116 |
68
+ | 0.7983 | 1.8388 | 1300 | 0.4960 | 0.3872 |
69
+ | 0.7983 | 1.9802 | 1400 | 0.4857 | 0.3868 |
70
+ | 0.6274 | 2.1216 | 1500 | 0.4689 | 0.3656 |
71
+ | 0.6274 | 2.2631 | 1600 | 0.4680 | 0.3562 |
72
+ | 0.6274 | 2.4045 | 1700 | 0.4536 | 0.3535 |
73
+ | 0.6274 | 2.5460 | 1800 | 0.4486 | 0.3501 |
74
+ | 0.6274 | 2.6874 | 1900 | 0.4396 | 0.3505 |
75
+ | 0.4939 | 2.8289 | 2000 | 0.4299 | 0.3340 |
76
+ | 0.4939 | 2.9703 | 2100 | 0.4292 | 0.3311 |
77
+ | 0.4939 | 3.1117 | 2200 | 0.4276 | 0.3271 |
78
+ | 0.4939 | 3.2532 | 2300 | 0.4233 | 0.3260 |
79
+ | 0.4939 | 3.3946 | 2400 | 0.4192 | 0.3223 |
80
+ | 0.4072 | 3.5361 | 2500 | 0.4179 | 0.3195 |
81
+ | 0.4072 | 3.6775 | 2600 | 0.4159 | 0.3171 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f04f1b6aefe836dda05067bd79e621d1ad4befba35e8b56054b1d1e9017790ec
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f3006014cd8cde77120d479e9ff74c2e1a5d6ef9a7faed2b0549f83d29d6de
3
  size 1261975580
runs/May17_07-56-01_2e698a9c250f/events.out.tfevents.1715929316.2e698a9c250f.3965.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e3b0d7aba5a35db42e0e264876894fb6f304e06bea00a6a0031e47534cbad3e
3
- size 14895
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21d893d8a7266b058e46e1f9557e80733eac5018557daecb272f91bb455563d
3
+ size 16096