thirty_wav2vec2_ft_960h_no_lm
Browse files- README.md +10 -10
- config.json +1 -2
- model.safetensors +1 -1
- runs/Apr12_21-51-44_nfcbsu9pri/events.out.tfevents.1712959407.nfcbsu9pri.32.0 +3 -0
- training_args.bin +1 -1
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
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer:
|
22 |
-
- Cer:
|
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 |
-
-
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
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":
|
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:
|
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:
|
3 |
size 4527
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45fc5858186fda138bced49e325683ff1c6a71f47398af284e78caeff0db6a4d
|
3 |
size 4527
|