Commit
•
cb7b0f3
1
Parent(s):
c86d7d8
End of training
Browse files- README.md +31 -0
- model-00001-of-00002.safetensors +1 -1
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
base_model: openai/whisper-large-v3
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: voice-clone-large-finetune
|
| 9 |
results: []
|
|
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# voice-clone-large-finetune
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -46,6 +51,32 @@ The following hyperparameters were used during training:
|
|
| 46 |
- training_steps: 5000
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.45.2
|
|
|
|
| 4 |
base_model: openai/whisper-large-v3
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: voice-clone-large-finetune
|
| 11 |
results: []
|
|
|
|
| 18 |
# voice-clone-large-finetune
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4491
|
| 23 |
+
- Wer: 16.9582
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 51 |
- training_steps: 5000
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 57 |
+
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
| 58 |
+
| 0.1608 | 0.8460 | 250 | 0.5171 | 25.8227 |
|
| 59 |
+
| 0.0607 | 1.6920 | 500 | 0.4735 | 28.3427 |
|
| 60 |
+
| 0.0255 | 2.5381 | 750 | 0.4274 | 25.4966 |
|
| 61 |
+
| 0.0138 | 3.3841 | 1000 | 0.4327 | 18.9742 |
|
| 62 |
+
| 0.0013 | 4.2301 | 1250 | 0.4508 | 20.8123 |
|
| 63 |
+
| 0.0129 | 5.0761 | 1500 | 0.4107 | 21.2274 |
|
| 64 |
+
| 0.0005 | 5.9222 | 1750 | 0.4218 | 21.5535 |
|
| 65 |
+
| 0.0018 | 6.7682 | 2000 | 0.4256 | 17.5215 |
|
| 66 |
+
| 0.0021 | 7.6142 | 2250 | 0.4224 | 18.1441 |
|
| 67 |
+
| 0.0015 | 8.4602 | 2500 | 0.4298 | 18.0255 |
|
| 68 |
+
| 0.0008 | 9.3063 | 2750 | 0.4376 | 18.1441 |
|
| 69 |
+
| 0.0005 | 10.1523 | 3000 | 0.4418 | 17.6697 |
|
| 70 |
+
| 0.0014 | 10.9983 | 3250 | 0.4442 | 17.5808 |
|
| 71 |
+
| 0.0002 | 11.8443 | 3500 | 0.4422 | 17.1064 |
|
| 72 |
+
| 0.0009 | 12.6904 | 3750 | 0.4408 | 17.1657 |
|
| 73 |
+
| 0.0002 | 13.5364 | 4000 | 0.4438 | 16.9878 |
|
| 74 |
+
| 0.0009 | 14.3824 | 4250 | 0.4452 | 16.7803 |
|
| 75 |
+
| 0.0007 | 15.2284 | 4500 | 0.4457 | 16.8989 |
|
| 76 |
+
| 0.0 | 16.0745 | 4750 | 0.4485 | 16.8693 |
|
| 77 |
+
| 0.0 | 16.9205 | 5000 | 0.4491 | 16.9582 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
### Framework versions
|
| 81 |
|
| 82 |
- Transformers 4.45.2
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4993448880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2fdd196e191230474e5acb7a2389a57f4b6a1d60f554de108803d825783a4ff
|
| 3 |
size 4993448880
|