End of training
Browse files- README.md +22 -14
- config.json +3 -3
- model.safetensors +2 -2
- runs/Jun30_12-30-38_d104d5d394a4/events.out.tfevents.1719750711.d104d5d394a4.945.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
-
base_model: Thienpkae/wav2vec2-large-xls-r-vi-colab
|
3 |
license: apache-2.0
|
4 |
-
|
5 |
-
- wer
|
6 |
tags:
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-vi-colab
|
10 |
results: []
|
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# wav2vec2-large-xls-r-vi-colab
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer: 0
|
22 |
-
- Cer: 0
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -44,18 +44,26 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- lr_scheduler_warmup_steps:
|
48 |
- num_epochs: 30
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
|
|
56 |
-
| 3.
|
57 |
-
| 3.
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-vi-colab
|
10 |
results: []
|
|
|
15 |
|
16 |
# wav2vec2-large-xls-r-vi-colab
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 4.5540
|
21 |
+
- Wer: 1.0
|
22 |
+
- Cer: 1.0
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 500
|
48 |
- num_epochs: 30
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
54 |
+
|:-------------:|:-------:|:----:|:---------------:|:---:|:---:|
|
55 |
+
| 9.6481 | 2.3864 | 315 | 4.4676 | 1.0 | 1.0 |
|
56 |
+
| 3.8703 | 4.7727 | 630 | 4.4033 | 1.0 | 1.0 |
|
57 |
+
| 3.4149 | 7.1591 | 945 | 4.7546 | 1.0 | 1.0 |
|
58 |
+
| 3.4323 | 9.5455 | 1260 | 4.2532 | 1.0 | 1.0 |
|
59 |
+
| 3.4127 | 11.9318 | 1575 | 4.6692 | 1.0 | 1.0 |
|
60 |
+
| 3.4185 | 14.3182 | 1890 | 4.3411 | 1.0 | 1.0 |
|
61 |
+
| 3.4112 | 16.7045 | 2205 | 4.5614 | 1.0 | 1.0 |
|
62 |
+
| 3.4074 | 19.0909 | 2520 | 4.3545 | 1.0 | 1.0 |
|
63 |
+
| 3.4073 | 21.4773 | 2835 | 4.4929 | 1.0 | 1.0 |
|
64 |
+
| 3.4004 | 23.8636 | 3150 | 4.6089 | 1.0 | 1.0 |
|
65 |
+
| 3.4099 | 26.25 | 3465 | 4.5189 | 1.0 | 1.0 |
|
66 |
+
| 3.3972 | 28.6364 | 3780 | 4.5540 | 1.0 | 1.0 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
@@ -87,7 +87,7 @@
|
|
87 |
"num_hidden_layers": 12,
|
88 |
"num_negatives": 100,
|
89 |
"output_hidden_size": 768,
|
90 |
-
"pad_token_id":
|
91 |
"proj_codevector_dim": 256,
|
92 |
"tdnn_dilation": [
|
93 |
1,
|
@@ -113,6 +113,6 @@
|
|
113 |
"torch_dtype": "float32",
|
114 |
"transformers_version": "4.41.2",
|
115 |
"use_weighted_layer_sum": false,
|
116 |
-
"vocab_size":
|
117 |
"xvector_output_dim": 512
|
118 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
|
|
87 |
"num_hidden_layers": 12,
|
88 |
"num_negatives": 100,
|
89 |
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 92,
|
91 |
"proj_codevector_dim": 256,
|
92 |
"tdnn_dilation": [
|
93 |
1,
|
|
|
113 |
"torch_dtype": "float32",
|
114 |
"transformers_version": "4.41.2",
|
115 |
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 95,
|
117 |
"xvector_output_dim": 512
|
118 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a989d17eaeaf2ffd399f853c680ae8d26f52e45bb0a0d50e97feec5a04b21576
|
3 |
+
size 377804916
|
runs/Jun30_12-30-38_d104d5d394a4/events.out.tfevents.1719750711.d104d5d394a4.945.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45f8566aafb0ddb738e07260a5c27f3228420d00f33207ac596c9eba6b9367f5
|
3 |
+
size 13814
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16eb319d9dacd339990dc6b25e8c325031ef603f003ee8b8f4e2d55bb83f3f2f
|
3 |
size 5112
|