End of training
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,23 +44,25 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 100
|
47 |
-
- training_steps:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
-
- Transformers 4.
|
64 |
-
- Pytorch 2.5.1+
|
65 |
- Datasets 3.3.2
|
66 |
- Tokenizers 0.21.0
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0726
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 100
|
47 |
+
- training_steps: 700
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.0676 | 100.0 | 100 | 0.9818 |
|
55 |
+
| 0.0619 | 200.0 | 200 | 1.0659 |
|
56 |
+
| 0.0528 | 300.0 | 300 | 1.0396 |
|
57 |
+
| 0.0501 | 400.0 | 400 | 1.0640 |
|
58 |
+
| 0.0517 | 500.0 | 500 | 1.0363 |
|
59 |
+
| 0.0435 | 600.0 | 600 | 1.0726 |
|
60 |
+
| 0.0426 | 700.0 | 700 | 1.0726 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
+
- Transformers 4.48.3
|
66 |
+
- Pytorch 2.5.1+cu124
|
67 |
- Datasets 3.3.2
|
68 |
- Tokenizers 0.21.0
|
generation_config.json
CHANGED
@@ -5,5 +5,5 @@
|
|
5 |
"eos_token_id": 2,
|
6 |
"max_length": 1876,
|
7 |
"pad_token_id": 1,
|
8 |
-
"transformers_version": "4.
|
9 |
}
|
|
|
5 |
"eos_token_id": 2,
|
6 |
"max_length": 1876,
|
7 |
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.48.3"
|
9 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b1775ab0673c93f47a1ec3c84442d376ef5e0f92230af7f7ec2b82ac0dd1fcd
|
3 |
size 577789320
|
runs/Mar07_12-56-54_ce0a8580c787/events.out.tfevents.1741352228.ce0a8580c787.272.0
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:ea20d226d2d4bbefc3ae251a535eea18b2dfb16c070ec9c586f568e699d71295
|
3 |
+
size 14847
|