End of training
Browse files
README.md
CHANGED
|
@@ -20,7 +20,12 @@ 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 VoxPopuli dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -46,19 +51,9 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 500
|
| 49 |
-
- training_steps:
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
-
| 0.5279 | 8.55 | 1000 | 0.4791 |
|
| 57 |
-
| 0.4992 | 17.09 | 2000 | 0.4619 |
|
| 58 |
-
| 0.4883 | 25.64 | 3000 | 0.4586 |
|
| 59 |
-
| 0.4804 | 34.19 | 4000 | 0.4567 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.38.0.dev0
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- eval_loss: 0.4728
|
| 24 |
+
- eval_runtime: 4.3194
|
| 25 |
+
- eval_samples_per_second: 191.232
|
| 26 |
+
- eval_steps_per_second: 24.078
|
| 27 |
+
- epoch: 1273.5
|
| 28 |
+
- step: 149000
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 500
|
| 54 |
+
- training_steps: 150000
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.38.0.dev0
|
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 sha256:94b5bd2380f03b6439d5a2a61017a0a4d31d126f7b1c5b2790fb0b17cbf54ab5
|
| 3 |
size 577789320
|
runs/Feb09_15-35-25_dgxa100/events.out.tfevents.1707489328.dgxa100
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 sha256:058634b1d147bca8df4433606eeff1ea84a133f7766448c8438adcad1d28f3aa
|
| 3 |
+
size 1002351
|