ImanNalia commited on
Commit
c042bc9
1 Parent(s): 1366ae8

thirty_wav2vec2_ft_960h_no_lm

Browse files
README.md CHANGED
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 960h
17
 
18
- This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2440
21
- - Wer: 40.5592
22
- - Cer: 21.2837
23
 
24
  ## Model description
25
 
@@ -45,17 +45,17 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 2000
48
- - num_epochs: 50
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
- | 6.4178 | 9.26 | 500 | 3.0304 | 100.0 | 99.0785 |
55
- | 3.418 | 18.52 | 1000 | 2.9473 | 100.0 | 99.0785 |
56
- | 2.3895 | 27.78 | 1500 | 1.1051 | 47.8959 | 24.0394 |
57
- | 0.8914 | 37.04 | 2000 | 1.2159 | 43.2724 | 22.3298 |
58
- | 0.5237 | 46.3 | 2500 | 1.2440 | 40.5592 | 21.2837 |
59
 
60
 
61
  ### Framework versions
 
15
 
16
  # 960h
17
 
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5325
21
+ - Wer: 24.4442
22
+ - Cer: 12.0113
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 2000
48
+ - training_steps: 2700
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
54
+ | 1.0759 | 1.75 | 500 | 0.7781 | 32.9761 | 16.6493 |
55
+ | 0.8049 | 3.51 | 1000 | 0.6552 | 29.8584 | 14.9333 |
56
+ | 0.7047 | 5.26 | 1500 | 0.6050 | 27.5232 | 13.6151 |
57
+ | 0.6339 | 7.02 | 2000 | 0.5865 | 26.3889 | 13.1279 |
58
+ | 0.5331 | 8.77 | 2500 | 0.5325 | 24.4442 | 12.0113 |
59
 
60
 
61
  ### Framework versions
config.json CHANGED
@@ -46,7 +46,6 @@
46
  "ctc_zero_infinity": false,
47
  "diversity_loss_weight": 0.1,
48
  "do_stable_layer_norm": false,
49
- "dropout": 0.2,
50
  "eos_token_id": 2,
51
  "feat_extract_activation": "gelu",
52
  "feat_extract_dropout": 0.0,
@@ -80,7 +79,7 @@
80
  "num_hidden_layers": 12,
81
  "num_negatives": 100,
82
  "output_hidden_size": 768,
83
- "pad_token_id": 29,
84
  "proj_codevector_dim": 256,
85
  "tdnn_dilation": [
86
  1,
 
46
  "ctc_zero_infinity": false,
47
  "diversity_loss_weight": 0.1,
48
  "do_stable_layer_norm": false,
 
49
  "eos_token_id": 2,
50
  "feat_extract_activation": "gelu",
51
  "feat_extract_dropout": 0.0,
 
79
  "num_hidden_layers": 12,
80
  "num_negatives": 100,
81
  "output_hidden_size": 768,
82
+ "pad_token_id": 0,
83
  "proj_codevector_dim": 256,
84
  "tdnn_dilation": [
85
  1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5029fdeb581adcea5ec74b2f9910d8cee2fcebf811370b61c33549dede02bab
3
  size 377611072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f386037321e42c35e56cc1a6297492bc34f2132087370d35c19578a0f7ba11
3
  size 377611072
runs/Apr12_21-51-44_nfcbsu9pri/events.out.tfevents.1712959407.nfcbsu9pri.32.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364bf2a2794d323aea64215a163d4538a0c5d3a34f4277add5f14b99cae4a518
3
+ size 9305
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfb5c0eb77e58041b909c67ec1b153af12cc6bf49d7a2441bf62a403ef22f9e2
3
  size 4527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fc5858186fda138bced49e325683ff1c6a71f47398af284e78caeff0db6a4d
3
  size 4527