Commit
·
662cba0
1
Parent(s):
dd459df
Model save
Browse files
README.md
CHANGED
|
@@ -1,26 +1,21 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
license: mit
|
| 5 |
base_model: microsoft/speecht5_tts
|
| 6 |
tags:
|
| 7 |
-
- en_accent,mozilla,t5,common_voice_1_0
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
-
-
|
| 11 |
model-index:
|
| 12 |
-
- name:
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
-
#
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.4530
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -48,23 +43,11 @@ The following hyperparameters were used during training:
|
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_steps: 500
|
| 51 |
-
-
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
| 58 |
-
| 0.5188 | 3.9 | 1000 | 0.4639 |
|
| 59 |
-
| 0.4705 | 7.8 | 2000 | 0.4534 |
|
| 60 |
-
| 0.4559 | 11.7 | 3000 | 0.4463 |
|
| 61 |
-
| 0.4763 | 15.59 | 4000 | 0.4477 |
|
| 62 |
-
| 0.4549 | 19.49 | 5000 | 0.4474 |
|
| 63 |
-
| 0.4684 | 23.39 | 6000 | 0.4580 |
|
| 64 |
-
| 0.4471 | 27.29 | 7000 | 0.4468 |
|
| 65 |
-
| 0.4666 | 31.19 | 8000 | 0.4472 |
|
| 66 |
-
| 0.4338 | 35.09 | 9000 | 0.4515 |
|
| 67 |
-
| 0.4452 | 38.99 | 10000 | 0.4530 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model: microsoft/speecht5_tts
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- common_voice_1_0
|
| 8 |
model-index:
|
| 9 |
+
- name: speecht5_tts
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# speecht5_tts
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_1_0 dataset.
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 3.0
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### 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:e6f89ca67149df0507dd933f3fa9fe01e2e6025c787f48c7cb45d8b3c303fa3d
|
| 3 |
size 577789320
|
runs/Nov16_17-54-07_instance-2/events.out.tfevents.1700157247.instance-2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ae67aeaea7011529cef3f93e9f5e802d99a0a01266afbbb17869fc923c353e
|
| 3 |
+
size 30122
|
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 sha256:9ae7168bc510d2d6e3e2a24edc495cb219ba6cf6e270925e5fff687b3bfcba99
|
| 3 |
+
size 4792
|