Commit ·
75e1df2
1
Parent(s): cf7fac1
End of training
Browse files- README.md +28 -10
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,28 +1,27 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-large-v3
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/maxhar/whisper_largev3-dv-finetuning/runs/
|
| 15 |
-
#
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
- eval_runtime: 143.56
|
| 22 |
-
- eval_samples_per_second: 0.697
|
| 23 |
-
- eval_steps_per_second: 0.021
|
| 24 |
-
- epoch: 11.8632
|
| 25 |
-
- step: 3900
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -51,6 +50,25 @@ The following hyperparameters were used during training:
|
|
| 51 |
- training_steps: 4000
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.41.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- dv
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: openai/whisper-large-v3
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
model-index:
|
| 11 |
+
- name: Whisper Large v3 DV - Alakxender
|
| 12 |
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/maxhar/whisper_largev3-dv-finetuning/runs/a8ygosbx)
|
| 19 |
+
# Whisper Large v3 DV - Alakxender
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4610
|
| 24 |
+
- Wer: 71.0345
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 50 |
- training_steps: 4000
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 57 |
+
| 1.4644 | 0.9772 | 300 | 1.0654 | 203.9655 |
|
| 58 |
+
| 0.2384 | 1.9544 | 600 | 0.3342 | 84.8276 |
|
| 59 |
+
| 0.1481 | 2.9316 | 900 | 0.2715 | 78.7931 |
|
| 60 |
+
| 0.0975 | 2.9772 | 1200 | 0.2635 | 76.0345 |
|
| 61 |
+
| 0.0616 | 3.9544 | 1500 | 0.2841 | 73.1034 |
|
| 62 |
+
| 0.0399 | 4.9772 | 1800 | 0.3215 | 72.2414 |
|
| 63 |
+
| 0.0218 | 5.9772 | 2100 | 0.3881 | 73.7931 |
|
| 64 |
+
| 0.046 | 6.9772 | 2400 | 0.2772 | 74.1379 |
|
| 65 |
+
| 0.018 | 7.9544 | 2700 | 0.3344 | 71.3793 |
|
| 66 |
+
| 0.0067 | 8.9316 | 3000 | 0.3947 | 71.7241 |
|
| 67 |
+
| 0.0023 | 9.9088 | 3300 | 0.4246 | 72.5862 |
|
| 68 |
+
| 0.0008 | 10.8860 | 3600 | 0.4503 | 71.7241 |
|
| 69 |
+
| 0.0003 | 11.8632 | 3900 | 0.4610 | 71.0345 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- Transformers 4.41.0.dev0
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81cc9f4ca8fe9ffde671a5ae57a131635a861a7005b87ea70c7c4f8f4b0476a8
|
| 3 |
+
size 4993448880
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:629aa0d78f00e45119246837079103bcb73c42c2289370aebfa4ab1627bbfc64
|
| 3 |
+
size 1180663192
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93155cbf2f42b5bdca94ac9032a686f40fdb90d96687ebcb16b99fee1458679c
|
| 3 |
+
size 5240
|