Hugging Face's logo

TheRamsay
/
wav2vec2-ctc

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
TheRamsay commited on
Commit
1a1f76a
·
verified ·
1 Parent(s): 1ff7361

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. README.md +10 -15
  2. config.json +4 -4
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
  This model is a fine-tuned version of [fav-kky/wav2vec2-base-cs-80k-ClTRUS](https://huggingface.co/fav-kky/wav2vec2-base-cs-80k-ClTRUS) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: inf
22
- - Wer: 1.0555
23
 
24
  ## Model description
25
 
@@ -38,28 +38,23 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
- - train_batch_size: 16
43
- - eval_batch_size: 16
44
  - seed: 42
45
  - gradient_accumulation_steps: 2
46
- - total_train_batch_size: 32
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_ratio: 0.2
50
- - num_epochs: 20
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-------:|:----:|:---------------:|:------:|
57
- | 0.0 | 3.1949 | 500 | inf | 1.0555 |
58
- | 0.0 | 6.3898 | 1000 | inf | 1.0555 |
59
- | 0.0 | 9.5847 | 1500 | inf | 1.0555 |
60
- | 0.0 | 12.7796 | 2000 | inf | 1.0555 |
61
- | 0.0 | 15.9744 | 2500 | inf | 1.0555 |
62
- | 0.0 | 19.1693 | 3000 | inf | 1.0555 |
63
 
64
 
65
  ### Framework versions
 
19
  This model is a fine-tuned version of [fav-kky/wav2vec2-base-cs-80k-ClTRUS](https://huggingface.co/fav-kky/wav2vec2-base-cs-80k-ClTRUS) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: inf
22
+ - Wer: 1.0
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 4
44
  - seed: 42
45
  - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 8
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.3
50
+ - num_epochs: 5
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
57
+ | 650.6179 | 4.0 | 500 | inf | 1.0 |
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -42,9 +42,9 @@
42
  2,
43
  2
44
  ],
45
- "ctc_loss_reduction": "sum",
46
  "ctc_zero_infinity": false,
47
- "decoder_start_token_id": 50,
48
  "diversity_loss_weight": 0.1,
49
  "do_stable_layer_norm": false,
50
  "eos_token_id": 2,
@@ -77,7 +77,7 @@
77
  "num_hidden_layers": 6,
78
  "num_negatives": 100,
79
  "output_hidden_size": 768,
80
- "pad_token_id": 49,
81
  "proj_codevector_dim": 256,
82
  "tdnn_dilation": [
83
  1,
@@ -103,6 +103,6 @@
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.45.2",
105
  "use_weighted_layer_sum": false,
106
- "vocab_size": 52,
107
  "xvector_output_dim": 512
108
  }
 
42
  2,
43
  2
44
  ],
45
+ "ctc_loss_reduction": "mean",
46
  "ctc_zero_infinity": false,
47
+ "decoder_start_token_id": 43,
48
  "diversity_loss_weight": 0.1,
49
  "do_stable_layer_norm": false,
50
  "eos_token_id": 2,
 
77
  "num_hidden_layers": 6,
78
  "num_negatives": 100,
79
  "output_hidden_size": 768,
80
+ "pad_token_id": 42,
81
  "proj_codevector_dim": 256,
82
  "tdnn_dilation": [
83
  1,
 
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.45.2",
105
  "use_weighted_layer_sum": false,
106
+ "vocab_size": 45,
107
  "xvector_output_dim": 512
108
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32c5df6b29386e3581bae9e108f81b3403c666e7490422494e155844b236d9ef
3
- size 65000248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05674d5b7b603a3e51d220c23c3c645e44b702c50e7e57e90880be0a5c196dc8
3
+ size 64989468
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30ee42f67045bba106f47f0f6f5f062c3e5114c16ce8a08158710f7262318745
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90038c0fc2656f331005268e5bcd90aad755a09be99dbe75ab03240634580813
3
  size 5176