Commit
•
a0b1bd1
1
Parent(s):
962ccb7
update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,24 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- PolyAI/minds14
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: whisper-tiny-en-minds14
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,6 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# whisper-tiny-en-minds14
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -42,13 +61,22 @@ The following hyperparameters were used during training:
|
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: constant_with_warmup
|
| 44 |
- lr_scheduler_warmup_steps: 50
|
| 45 |
-
- training_steps:
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- PolyAI/minds14
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: whisper-tiny-en-minds14
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: PolyAI/minds14
|
| 17 |
+
type: PolyAI/minds14
|
| 18 |
+
config: en-US
|
| 19 |
+
split: train
|
| 20 |
+
args: en-US
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.2744982290436836
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
# whisper-tiny-en-minds14
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.5680
|
| 35 |
+
- Wer Ortho: 0.2721
|
| 36 |
+
- Wer: 0.2745
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: constant_with_warmup
|
| 63 |
- lr_scheduler_warmup_steps: 50
|
| 64 |
+
- training_steps: 500
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
| 70 |
+
| 1.4576 | 1.79 | 50 | 0.9286 | 0.3128 | 0.3152 |
|
| 71 |
+
| 0.3694 | 3.57 | 100 | 0.5188 | 0.2776 | 0.2774 |
|
| 72 |
+
| 0.0466 | 5.36 | 150 | 0.4494 | 0.2640 | 0.2692 |
|
| 73 |
+
| 0.008 | 7.14 | 200 | 0.4855 | 0.2782 | 0.2816 |
|
| 74 |
+
| 0.0026 | 8.93 | 250 | 0.4892 | 0.2801 | 0.2845 |
|
| 75 |
+
| 0.0016 | 10.71 | 300 | 0.5116 | 0.2745 | 0.2774 |
|
| 76 |
+
| 0.0004 | 12.5 | 350 | 0.5383 | 0.2770 | 0.2798 |
|
| 77 |
+
| 0.0002 | 14.29 | 400 | 0.5471 | 0.2758 | 0.2774 |
|
| 78 |
+
| 0.0002 | 16.07 | 450 | 0.5590 | 0.2714 | 0.2733 |
|
| 79 |
+
| 0.0001 | 17.86 | 500 | 0.5680 | 0.2721 | 0.2745 |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|