Hugging Face's logo

gweltou
/
mHuBERT-147-br

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Breton
hubert
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gweltou commited on
Commit
b9c0e02
•
1 Parent(s): 3e374fb

End of training

Browse files
Files changed (20) hide show
  1. README.md +13 -49
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Jun22_17-02-55_gweltaz-NUC10i7FNK/events.out.tfevents.1719068720.gweltaz-NUC10i7FNK.4137.0 +3 -0
  5. runs/Jun22_18-01-30_gweltaz-NUC10i7FNK/events.out.tfevents.1719072217.gweltaz-NUC10i7FNK.4586.0 +3 -0
  6. runs/Jun22_20-35-39_gweltaz-NUC10i7FNK/events.out.tfevents.1719081455.gweltaz-NUC10i7FNK.2915.0 +3 -0
  7. runs/Jun22_22-15-24_gweltaz-NUC10i7FNK/events.out.tfevents.1719087445.gweltaz-NUC10i7FNK.3959.0 +3 -0
  8. runs/Jun22_23-11-25_gweltaz-NUC10i7FNK/events.out.tfevents.1719090821.gweltaz-NUC10i7FNK.5315.0 +3 -0
  9. runs/Jun23_07-07-31_gweltaz-NUC10i7FNK/events.out.tfevents.1719119457.gweltaz-NUC10i7FNK.2675.0 +3 -0
  10. runs/Jun23_08-09-49_gweltaz-NUC10i7FNK/events.out.tfevents.1719123124.gweltaz-NUC10i7FNK.3901.0 +3 -0
  11. runs/Jun23_09-16-47_gweltaz-NUC10i7FNK/events.out.tfevents.1719127128.gweltaz-NUC10i7FNK.4397.0 +3 -0
  12. runs/Jun23_18-50-29_gweltaz-NUC10i7FNK/events.out.tfevents.1719161546.gweltaz-NUC10i7FNK.2087.0 +3 -0
  13. runs/Jun23_21-00-18_gweltaz-NUC10i7FNK/events.out.tfevents.1719169372.gweltaz-NUC10i7FNK.2496.0 +3 -0
  14. runs/Jun29_16-58-50_gweltaz-NUC10i7FNK/events.out.tfevents.1719673252.gweltaz-NUC10i7FNK.3384.0 +3 -0
  15. runs/Jun29_18-46-04_gweltaz-NUC10i7FNK/events.out.tfevents.1719679677.gweltaz-NUC10i7FNK.2910.0 +3 -0
  16. runs/Jun29_20-12-42_gweltaz-NUC10i7FNK/events.out.tfevents.1719684885.gweltaz-NUC10i7FNK.1994.0 +3 -0
  17. runs/Jun30_08-50-31_gweltaz-NUC10i7FNK/events.out.tfevents.1719730341.gweltaz-NUC10i7FNK.2969.0 +3 -0
  18. runs/Jun30_10-07-27_gweltaz-NUC10i7FNK/events.out.tfevents.1719734981.gweltaz-NUC10i7FNK.2594.0 +3 -0
  19. runs/Jun30_11-35-47_gweltaz-NUC10i7FNK/events.out.tfevents.1719740265.gweltaz-NUC10i7FNK.2920.0 +3 -0
  20. training_args.bin +1 -1
README.md CHANGED
@@ -1,28 +1,11 @@
1
  ---
2
  license: cc-by-nc-4.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: utter-project/mHuBERT-147
6
- datasets:
7
- - common_voice_15_0
8
- metrics:
9
- - wer
10
  model-index:
11
  - name: mHuBERT-147-br
12
- results:
13
- - task:
14
- type: automatic-speech-recognition
15
- name: Automatic Speech Recognition
16
- dataset:
17
- name: common_voice_15_0
18
- type: common_voice_15_0
19
- config: br
20
- split: None
21
- args: br
22
- metrics:
23
- - type: wer
24
- value: 53.76572908956329
25
- name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +13,16 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # mHuBERT-147-br
32
 
33
- This model is a fine-tuned version of [utter-project/mHuBERT-147](https://huggingface.co/utter-project/mHuBERT-147) on the common_voice_15_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7650
36
- - Wer: 53.7657
37
- - Cer: 18.3841
 
 
 
 
 
38
 
39
  ## Model description
40
 
@@ -53,7 +41,7 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 3.7e-05
57
  - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
@@ -62,33 +50,9 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
- - num_epochs: 40
66
  - mixed_precision_training: Native AMP
67
 
68
- ### Training results
69
-
70
- | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
71
- |:-------------:|:-----:|:-----:|:-------:|:---------------:|:-------:|
72
- | 6.5746 | 2.18 | 1000 | 99.8848 | 3.8929 | 100.0 |
73
- | 2.8591 | 4.36 | 2000 | 51.1549 | 1.8873 | 97.5296 |
74
- | 1.4189 | 6.54 | 3000 | 27.4120 | 1.0985 | 77.2853 |
75
- | 0.9787 | 8.71 | 4000 | 0.8995 | 71.3360 | 24.4590 |
76
- | 0.803 | 10.89 | 5000 | 0.8429 | 67.1817 | 22.9902 |
77
- | 0.718 | 13.07 | 6000 | 0.8035 | 63.8879 | 21.6750 |
78
- | 0.6359 | 15.25 | 7000 | 0.7927 | 62.2502 | 21.1144 |
79
- | 0.5832 | 17.43 | 8000 | 0.7508 | 60.3072 | 20.3406 |
80
- | 0.555 | 19.61 | 9000 | 0.7509 | 58.7990 | 19.8568 |
81
- | 0.5167 | 21.79 | 10000 | 0.7757 | 58.0218 | 19.7569 |
82
- | 0.4917 | 23.97 | 11000 | 0.7588 | 56.9671 | 19.4574 |
83
- | 0.4629 | 26.14 | 12000 | 0.7710 | 55.6255 | 19.0792 |
84
- | 0.4454 | 28.32 | 13000 | 0.7546 | 55.0888 | 18.8257 |
85
- | 0.4235 | 30.5 | 14000 | 0.7548 | 54.9963 | 18.7240 |
86
- | 0.4135 | 32.68 | 15000 | 0.7689 | 54.6725 | 18.6222 |
87
- | 0.411 | 34.86 | 16000 | 0.7619 | 54.4504 | 18.5320 |
88
- | 0.3934 | 37.04 | 17000 | 0.7621 | 53.9323 | 18.4014 |
89
- | 0.3912 | 39.22 | 18000 | 0.7650 | 53.7657 | 18.3841 |
90
-
91
-
92
  ### Framework versions
93
 
94
  - Transformers 4.39.1
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ base_model: utter-project/mHuBERT-147
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
6
  model-index:
7
  - name: mHuBERT-147-br
8
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
13
 
14
  # mHuBERT-147-br
15
 
16
+ This model is a fine-tuned version of [utter-project/mHuBERT-147](https://huggingface.co/utter-project/mHuBERT-147) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.7535
19
+ - eval_wer: 49.4962
20
+ - eval_cer: 16.3049
21
+ - eval_runtime: 61.2834
22
+ - eval_samples_per_second: 41.724
23
+ - eval_steps_per_second: 5.222
24
+ - epoch: 51.16
25
+ - step: 22000
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 3.8e-05
45
  - train_batch_size: 8
46
  - eval_batch_size: 8
47
  - seed: 42
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 52
54
  - mixed_precision_training: Native AMP
55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  ### Framework versions
57
 
58
  - Transformers 4.39.1
config.json CHANGED
@@ -67,10 +67,10 @@
67
  "num_conv_pos_embeddings": 128,
68
  "num_feat_extract_layers": 7,
69
  "num_hidden_layers": 12,
70
- "pad_token_id": 47,
71
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
72
  "torch_dtype": "float32",
73
  "transformers_version": "4.39.1",
74
  "use_weighted_layer_sum": false,
75
- "vocab_size": 50
76
  }
 
67
  "num_conv_pos_embeddings": 128,
68
  "num_feat_extract_layers": 7,
69
  "num_hidden_layers": 12,
70
+ "pad_token_id": 43,
71
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
72
  "torch_dtype": "float32",
73
  "transformers_version": "4.39.1",
74
  "use_weighted_layer_sum": false,
75
+ "vocab_size": 46
76
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:679fe2edaad5cf313e22103daf1dc446d7eaf6697635e4e4d0f8015e6d9ed73d
3
- size 377666024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c28649b520004d813849077ff8684cfcdd8395fcc91b0a73124ac9b5dc0cf3
3
+ size 377653720
runs/Jun22_17-02-55_gweltaz-NUC10i7FNK/events.out.tfevents.1719068720.gweltaz-NUC10i7FNK.4137.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dcf5ecc8764f323ddf2861f4fe566573f49ff8a3d2b1af980753cddfd33bcae
3
+ size 8432
runs/Jun22_18-01-30_gweltaz-NUC10i7FNK/events.out.tfevents.1719072217.gweltaz-NUC10i7FNK.4586.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41979ff376e76ed3da058eb28aea7d80823f1ea7626302456bda011ea60e2fcf
3
+ size 10736
runs/Jun22_20-35-39_gweltaz-NUC10i7FNK/events.out.tfevents.1719081455.gweltaz-NUC10i7FNK.2915.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea027cac07673c16b768a380e6a211d8977aae75a0ebff3f3c405f4ecc694c3
3
+ size 10736
runs/Jun22_22-15-24_gweltaz-NUC10i7FNK/events.out.tfevents.1719087445.gweltaz-NUC10i7FNK.3959.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ba24265b6e50d24dab8f4efa4f1bd93cba341a49a73b1e6477f371372a6313
3
+ size 7280
runs/Jun22_23-11-25_gweltaz-NUC10i7FNK/events.out.tfevents.1719090821.gweltaz-NUC10i7FNK.5315.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940255725b8165bbeb7083c9502aa7432d5d0732a145e12072e91225998d4788
3
+ size 6704
runs/Jun23_07-07-31_gweltaz-NUC10i7FNK/events.out.tfevents.1719119457.gweltaz-NUC10i7FNK.2675.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29c757ca0d01675f7a6d111f7aee16cd4377e7ecd20a758455e1fad9124f4a9
3
+ size 9008
runs/Jun23_08-09-49_gweltaz-NUC10i7FNK/events.out.tfevents.1719123124.gweltaz-NUC10i7FNK.3901.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75d05da1351df1be09e6208ca9209842fc428484bdfbde92417cf1ec9e5c601
3
+ size 9006
runs/Jun23_09-16-47_gweltaz-NUC10i7FNK/events.out.tfevents.1719127128.gweltaz-NUC10i7FNK.4397.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7415c9ab5155df8cb99a7588415acfbbc225ca0e68b961a616879297f00ef0
3
+ size 9008
runs/Jun23_18-50-29_gweltaz-NUC10i7FNK/events.out.tfevents.1719161546.gweltaz-NUC10i7FNK.2087.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f004ec792fc33badbdfe9b343a41a690515142888b79c1023a560f963a25e3c0
3
+ size 9584
runs/Jun23_21-00-18_gweltaz-NUC10i7FNK/events.out.tfevents.1719169372.gweltaz-NUC10i7FNK.2496.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876a35c5d5b73c4ffe90397ccddfa1515ade5124bd90f5541558192f2d9b913d
3
+ size 7280
runs/Jun29_16-58-50_gweltaz-NUC10i7FNK/events.out.tfevents.1719673252.gweltaz-NUC10i7FNK.3384.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4adea2ca3bb68908229ef460a63d775b60d0da6c445d859dd6b84df45682351a
3
+ size 6704
runs/Jun29_18-46-04_gweltaz-NUC10i7FNK/events.out.tfevents.1719679677.gweltaz-NUC10i7FNK.2910.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56e3797541607b6929bcf1e3668816e9252011ca65918e65c828c20fb6213b9
3
+ size 9008
runs/Jun29_20-12-42_gweltaz-NUC10i7FNK/events.out.tfevents.1719684885.gweltaz-NUC10i7FNK.1994.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1baf62c3acdb197be0cb59489a135412dcf5ddc4cb40c95ea5824a65abcef6c9
3
+ size 12508
runs/Jun30_08-50-31_gweltaz-NUC10i7FNK/events.out.tfevents.1719730341.gweltaz-NUC10i7FNK.2969.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65dbc52306a7659ee7b634c1d47a9af54c3cb8bd4e3da3ef894900cdf318d1d
3
+ size 9008
runs/Jun30_10-07-27_gweltaz-NUC10i7FNK/events.out.tfevents.1719734981.gweltaz-NUC10i7FNK.2594.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693ee2e9178df1380eeb782f65bf67e9a13ed2698d2c3f46f4113671a45690ce
3
+ size 9008
runs/Jun30_11-35-47_gweltaz-NUC10i7FNK/events.out.tfevents.1719740265.gweltaz-NUC10i7FNK.2920.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff93cc0498e2311d1ef5f94a4e214d8be6c399b8d139e16a2b910a28813db68e
3
+ size 6726
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd6ce8f68cff2c8c8cf8afeb1a27e6509fa58e65c7102f270f7d6e49e1c5cdab
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e74c30a88778b1a7803fec299849b4cf84371c5f9bdfd83edfbc35f75b84d82
3
  size 4475