End of training
Browse files- README.md +31 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-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: speech-synth-large-finetune
|
| 9 |
results: []
|
|
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# speech-synth-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 4.47.0
|
|
|
|
| 4 |
base_model: openai/whisper-large-v3
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: speech-synth-large-finetune
|
| 11 |
results: []
|
|
|
|
| 18 |
# speech-synth-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: 0.4259
|
| 23 |
+
- Wer: 16.8396
|
| 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 |
+
| 0.1313 | 0.7800 | 250 | 0.4953 | 30.7145 |
|
| 59 |
+
| 0.0531 | 1.5585 | 500 | 0.4647 | 28.1055 |
|
| 60 |
+
| 0.0269 | 2.3370 | 750 | 0.4448 | 19.9526 |
|
| 61 |
+
| 0.0101 | 3.1154 | 1000 | 0.4392 | 23.0062 |
|
| 62 |
+
| 0.0064 | 3.8955 | 1250 | 0.4053 | 22.2947 |
|
| 63 |
+
| 0.0057 | 4.6739 | 1500 | 0.4148 | 19.3003 |
|
| 64 |
+
| 0.0044 | 5.4524 | 1750 | 0.4028 | 17.9958 |
|
| 65 |
+
| 0.0047 | 6.2309 | 2000 | 0.4125 | 19.0631 |
|
| 66 |
+
| 0.003 | 7.0094 | 2250 | 0.3979 | 17.7883 |
|
| 67 |
+
| 0.0038 | 7.7894 | 2500 | 0.3923 | 20.5455 |
|
| 68 |
+
| 0.0 | 8.5679 | 2750 | 0.4077 | 17.6401 |
|
| 69 |
+
| 0.0002 | 9.3463 | 3000 | 0.4050 | 17.3733 |
|
| 70 |
+
| 0.0009 | 10.1248 | 3250 | 0.4101 | 17.0471 |
|
| 71 |
+
| 0.0005 | 10.9048 | 3500 | 0.4227 | 17.1954 |
|
| 72 |
+
| 0.0 | 11.6833 | 3750 | 0.4217 | 17.2250 |
|
| 73 |
+
| 0.0002 | 12.4618 | 4000 | 0.4241 | 17.0471 |
|
| 74 |
+
| 0.0 | 13.2402 | 4250 | 0.4239 | 16.9582 |
|
| 75 |
+
| 0.0005 | 14.0187 | 4500 | 0.4250 | 16.6617 |
|
| 76 |
+
| 0.0 | 14.7988 | 4750 | 0.4254 | 16.8396 |
|
| 77 |
+
| 0.0001 | 15.5772 | 5000 | 0.4259 | 16.8396 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
### Framework versions
|
| 81 |
|
| 82 |
- Transformers 4.47.0
|
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 sha256:459158f4f630826de794defd0f802cc62ec66568e848120f228d6227f907d9fd
|
| 3 |
size 4993448880
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1180663192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efc53feaf2d7b21ce258f62bc58eb4fef1940bd3938a43210e12fc33161fb96a
|
| 3 |
size 1180663192
|