Commit
•
525506b
1
Parent(s):
3817b73
End of training
Browse files
README.md
CHANGED
|
@@ -1,19 +1,41 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: poppysmickarlili/whisper-small-cantonese_02-05-2024-1727
|
| 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 |
-
#
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [poppysmickarlili/whisper-small-cantonese_02-05-2024-1727](https://huggingface.co/poppysmickarlili/whisper-small-cantonese_02-05-2024-1727) on
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -44,6 +66,16 @@ The following hyperparameters were used during training:
|
|
| 44 |
- training_steps: 4000
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.40.2
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- yue
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: poppysmickarlili/whisper-small-cantonese_02-05-2024-1727
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- mozilla-foundation/common_voice_17_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
model-index:
|
| 13 |
+
- name: Whisper Small Cantanese
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Common Voice 17.0
|
| 20 |
+
type: mozilla-foundation/common_voice_17_0
|
| 21 |
+
config: yue
|
| 22 |
+
split: None
|
| 23 |
+
args: 'config: yue, split: test'
|
| 24 |
+
metrics:
|
| 25 |
+
- name: Wer
|
| 26 |
+
type: wer
|
| 27 |
+
value: 57.34134434847916
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 31 |
should probably proofread and complete it, then remove this comment. -->
|
| 32 |
|
| 33 |
+
# Whisper Small Cantanese
|
| 34 |
|
| 35 |
+
This model is a fine-tuned version of [poppysmickarlili/whisper-small-cantonese_02-05-2024-1727](https://huggingface.co/poppysmickarlili/whisper-small-cantonese_02-05-2024-1727) on the Common Voice 17.0 dataset.
|
| 36 |
+
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.3536
|
| 38 |
+
- Wer: 57.3413
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
|
|
| 66 |
- training_steps: 4000
|
| 67 |
- mixed_precision_training: Native AMP
|
| 68 |
|
| 69 |
+
### Training results
|
| 70 |
+
|
| 71 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 72 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 73 |
+
| 0.0168 | 1.3908 | 1000 | 0.3280 | 59.7446 |
|
| 74 |
+
| 0.0046 | 2.7816 | 2000 | 0.3460 | 58.9185 |
|
| 75 |
+
| 0.0005 | 4.1725 | 3000 | 0.3504 | 57.1911 |
|
| 76 |
+
| 0.0002 | 5.5633 | 4000 | 0.3536 | 57.3413 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.40.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:224700d041fe832f9fa44649de85c22629b4c80beec2ed9a0015a9ccce5d718d
|
| 3 |
size 966995080
|
runs/May07_22-06-26_ip-10-0-11-199/events.out.tfevents.1715119621.ip-10-0-11-199.44258.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b04ee9f858f26c14b9f03db0e446346d3d5c5890b037069330c20a0b62b38c1e
|
| 3 |
+
size 42068
|