Model save
Browse files
README.md
CHANGED
@@ -1,9 +1,11 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
3 |
library_name: peft
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model: openai/whisper-small
|
7 |
model-index:
|
8 |
- name: whisper-small-finetuned
|
9 |
results: []
|
@@ -12,19 +14,19 @@ model-index:
|
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
-
[<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/keviinkibe/huggingface/runs/
|
16 |
-
[<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/keviinkibe/huggingface/runs/
|
17 |
# whisper-small-finetuned
|
18 |
|
19 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- eval_loss:
|
22 |
-
- eval_wer:
|
23 |
-
- eval_runtime:
|
24 |
-
- eval_samples_per_second: 0.
|
25 |
-
- eval_steps_per_second: 0.
|
26 |
-
- epoch:
|
27 |
-
- step:
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -43,14 +45,13 @@ More information needed
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
-
- learning_rate: 0.
|
47 |
-
- train_batch_size:
|
48 |
-
- eval_batch_size:
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
-
|
53 |
-
- training_steps: 2000
|
54 |
- mixed_precision_training: Native AMP
|
55 |
|
56 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: openai/whisper-small
|
3 |
+
datasets:
|
4 |
+
- common_voice_16_1
|
5 |
library_name: peft
|
6 |
+
license: apache-2.0
|
7 |
tags:
|
8 |
- generated_from_trainer
|
|
|
9 |
model-index:
|
10 |
- name: whisper-small-finetuned
|
11 |
results: []
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
[<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/keviinkibe/huggingface/runs/h79p39mv)
|
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/keviinkibe/huggingface/runs/h79p39mv)
|
19 |
# whisper-small-finetuned
|
20 |
|
21 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_1 dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- eval_loss: 4.5110
|
24 |
+
- eval_wer: 134.4828
|
25 |
+
- eval_runtime: 13.445
|
26 |
+
- eval_samples_per_second: 0.744
|
27 |
+
- eval_steps_per_second: 0.074
|
28 |
+
- epoch: 4.1
|
29 |
+
- step: 10
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
45 |
### Training hyperparameters
|
46 |
|
47 |
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 0.0001
|
49 |
+
- train_batch_size: 16
|
50 |
+
- eval_batch_size: 16
|
51 |
- seed: 42
|
52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
- lr_scheduler_type: linear
|
54 |
+
- training_steps: 20
|
|
|
55 |
- mixed_precision_training: Native AMP
|
56 |
|
57 |
### Framework versions
|