End of training
Browse files- README.md +29 -0
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -6,6 +6,11 @@ license: apache-2.0
|
|
| 6 |
base_model: openai/whisper-medium
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: ./whisper-medium-ea_5hr_v2
|
| 11 |
results: []
|
|
@@ -17,6 +22,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# ./whisper-medium-ea_5hr_v2
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Afrispeech-200 dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,6 +58,22 @@ The following hyperparameters were used during training:
|
|
| 45 |
- training_steps: 500
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.52.1
|
|
|
|
| 6 |
base_model: openai/whisper-medium
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
+
metrics:
|
| 10 |
+
- wer
|
| 11 |
+
- precision
|
| 12 |
+
- recall
|
| 13 |
+
- f1
|
| 14 |
model-index:
|
| 15 |
- name: ./whisper-medium-ea_5hr_v2
|
| 16 |
results: []
|
|
|
|
| 22 |
# ./whisper-medium-ea_5hr_v2
|
| 23 |
|
| 24 |
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Afrispeech-200 dataset.
|
| 25 |
+
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.4999
|
| 27 |
+
- Wer Ortho: 0.2185
|
| 28 |
+
- Wer: 0.1579
|
| 29 |
+
- Cer: 0.0705
|
| 30 |
+
- Precision: 0.9097
|
| 31 |
+
- Recall: 0.9048
|
| 32 |
+
- F1: 0.9068
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
|
|
|
| 58 |
- training_steps: 500
|
| 59 |
- mixed_precision_training: Native AMP
|
| 60 |
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | Cer | Precision | Recall | F1 |
|
| 64 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:---------:|:------:|:------:|
|
| 65 |
+
| 0.5036 | 0.1179 | 50 | 0.6665 | 0.2366 | 0.1752 | 0.0784 | 0.9011 | 0.8964 | 0.8982 |
|
| 66 |
+
| 0.5931 | 0.2358 | 100 | 0.5603 | 0.2211 | 0.1622 | 0.0689 | 0.9073 | 0.9022 | 0.9043 |
|
| 67 |
+
| 0.5468 | 0.3538 | 150 | 0.5329 | 0.2344 | 0.1807 | 0.0911 | 0.9033 | 0.8938 | 0.8974 |
|
| 68 |
+
| 0.5159 | 0.4717 | 200 | 0.5213 | 0.2247 | 0.1675 | 0.0814 | 0.9084 | 0.9044 | 0.9058 |
|
| 69 |
+
| 0.4744 | 0.5896 | 250 | 0.5160 | 0.2332 | 0.1703 | 0.0805 | 0.9064 | 0.8987 | 0.9016 |
|
| 70 |
+
| 0.4753 | 0.7075 | 300 | 0.5132 | 0.2116 | 0.1536 | 0.0661 | 0.9097 | 0.9061 | 0.9074 |
|
| 71 |
+
| 0.5142 | 0.8255 | 350 | 0.4989 | 0.2272 | 0.1646 | 0.0755 | 0.9063 | 0.9023 | 0.9036 |
|
| 72 |
+
| 0.4951 | 0.9434 | 400 | 0.4928 | 0.2152 | 0.1618 | 0.0713 | 0.9098 | 0.9062 | 0.9073 |
|
| 73 |
+
| 0.2467 | 1.0613 | 450 | 0.4990 | 0.2084 | 0.1510 | 0.0648 | 0.9155 | 0.9106 | 0.9126 |
|
| 74 |
+
| 0.211 | 1.1792 | 500 | 0.4999 | 0.2185 | 0.1579 | 0.0705 | 0.9097 | 0.9048 | 0.9068 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
### Framework versions
|
| 78 |
|
| 79 |
- Transformers 4.52.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055544304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e03c61457e1aed7d659de6025d5eaa93c29bd7470ee36d3257bf4294e7eb5104
|
| 3 |
size 3055544304
|