Commit
•
4e6e639
1
Parent(s):
09d78ae
Training in progress, step 4000
Browse files
README.md
CHANGED
|
@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# speecht5_tts_ta
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset.
|
| 20 |
-
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.5230
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -37,7 +35,7 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 41 |
- train_batch_size: 16
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
|
@@ -45,20 +43,9 @@ The following hyperparameters were used during training:
|
|
| 45 |
- total_train_batch_size: 32
|
| 46 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- lr_scheduler_warmup_steps: 1000
|
| 49 |
- training_steps: 4000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
-
| 0.9121 | 500.0 | 1000 | 0.4994 |
|
| 57 |
-
| 0.8363 | 1000.0 | 2000 | 0.5093 |
|
| 58 |
-
| 0.7777 | 1500.0 | 3000 | 0.5234 |
|
| 59 |
-
| 0.7586 | 2000.0 | 4000 | 0.5230 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.46.0.dev0
|
|
|
|
| 17 |
# speecht5_tts_ta
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
- train_batch_size: 16
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
|
|
|
| 43 |
- total_train_batch_size: 32
|
| 44 |
- optimizer: Use 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 |
- training_steps: 4000
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.46.0.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 sha256:5ffb108605d11a7e6967d411e96038a558d9c6678fae256fa759d4dec485ff55
|
| 3 |
size 577789320
|
runs/Oct24_08-17-22_2c77d78e9598/events.out.tfevents.1729757881.2c77d78e9598.341.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f3e61cc9a47ab3598d294d73ef4ac4871ade5e9234ff89b8ee70920e022ecd
|
| 3 |
+
size 41780
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b6d2270aa17081a51abe166a3fb5159a3e85a3c00fa7ece0555d2b836a5999a
|
| 3 |
size 5368
|