Commit
•
751f10d
1
Parent(s):
6032239
Training in progress, step 2000
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -40,26 +40,21 @@ More information needed
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 1e-05
|
43 |
-
- train_batch_size:
|
44 |
-
- eval_batch_size:
|
45 |
- seed: 42
|
46 |
- gradient_accumulation_steps: 2
|
47 |
-
- total_train_batch_size:
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
-
-
|
51 |
-
- training_steps: 5000
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
-
| 0.
|
59 |
-
| 0.5126 | 32.0 | 2000 | 0.4858 |
|
60 |
-
| 0.4753 | 48.0 | 3000 | 0.4889 |
|
61 |
-
| 0.4666 | 64.0 | 4000 | 0.4931 |
|
62 |
-
| 0.4836 | 80.0 | 5000 | 0.4982 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.7290
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 1e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
- seed: 42
|
46 |
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 16
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- training_steps: 100
|
|
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 0.7528 | 0.8 | 100 | 0.7290 |
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
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 sha256:7ae901514bbcaa5ea5d6f23cd4b029816c37553faa9cf097000f49560a7773a9
|
3 |
size 577789320
|
runs/Nov15_20-29-47_instance-2/events.out.tfevents.1700080187.instance-2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d76b5e4b97f8dbb0bdf1a6855bb5eafad74a93aa6feac7ffb5159e3fbae5a6d
|
3 |
+
size 16268
|
runs/Nov15_21-44-40_instance-2/events.out.tfevents.1700084681.instance-2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8b24db5e887f4512579a8fce51260e372d4d43c225ed6d4a3b976d465e7f66d
|
3 |
+
size 68820
|
training_args.bin
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 sha256:3f1a928718f65e4e008c23c0d206eba00b519ec39c82f17889e37c81edd16499
|
3 |
+
size 4728
|