Commit
•
f65d773
1
Parent(s):
78b0ec6
End of training
Browse files
README.md
CHANGED
|
@@ -8,9 +8,24 @@ tags:
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_16_1
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: Whisper Small Canontese X v1
|
| 13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# Whisper Small Canontese X v1
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -47,6 +65,15 @@ The following hyperparameters were used during training:
|
|
| 47 |
- training_steps: 3000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
### Framework versions
|
| 51 |
|
| 52 |
- Transformers 4.44.2
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_16_1
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
- name: Whisper Small Canontese X v1
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: Common Voice 11.0
|
| 21 |
+
type: mozilla-foundation/common_voice_16_1
|
| 22 |
+
config: zh-HK
|
| 23 |
+
split: None
|
| 24 |
+
args: 'config: zh-HK, split: test'
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 64.88730723606169
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
# Whisper Small Canontese X v1
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.2938
|
| 39 |
+
- Wer: 64.8873
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 65 |
- training_steps: 3000
|
| 66 |
- mixed_precision_training: Native AMP
|
| 67 |
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 72 |
+
| 0.4921 | 0.6196 | 1000 | 0.3749 | 74.5848 |
|
| 73 |
+
| 0.2181 | 1.2392 | 2000 | 0.3143 | 67.8529 |
|
| 74 |
+
| 0.1652 | 1.8587 | 3000 | 0.2938 | 64.8873 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
### Framework versions
|
| 78 |
|
| 79 |
- Transformers 4.44.2
|
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:e5e085b546ece878203195a5371f0c945120ba4f28b136736a9ebd5c3b0cbe93
|
| 3 |
size 966995080
|
runs/Sep24_15-58-39_b5bba1f1e1a8/events.out.tfevents.1727193522.b5bba1f1e1a8.1224.0
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 sha256:2625d1bfa755533abf302c2c9e16fd00a338f4184a16c1c36119ee747f572555
|
| 3 |
+
size 33295
|