Commit
•
1b8dc92
1
Parent(s):
19b88f1
Model save
Browse files- README.md +25 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,22 +1,24 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: openai/whisper-base.en
|
| 6 |
tags:
|
| 7 |
-
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
-
- name:
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 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 |
-
#
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -43,6 +45,23 @@ The following hyperparameters were used during training:
|
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_steps: 500
|
| 45 |
- training_steps: 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-base.en
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
+
- name: whisper-small-hi
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# whisper-small-hi
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0003
|
| 21 |
+
- Wer: 1.2422
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
- training_steps: 1000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 54 |
+
| 1.5447 | 33.33 | 100 | 1.2099 | 11.4907 |
|
| 55 |
+
| 0.4211 | 66.67 | 200 | 0.3868 | 1.5528 |
|
| 56 |
+
| 0.0987 | 100.0 | 300 | 0.0761 | 1.8634 |
|
| 57 |
+
| 0.006 | 133.33 | 400 | 0.0040 | 1.2422 |
|
| 58 |
+
| 0.0011 | 166.67 | 500 | 0.0010 | 1.2422 |
|
| 59 |
+
| 0.0006 | 200.0 | 600 | 0.0006 | 1.2422 |
|
| 60 |
+
| 0.0004 | 233.33 | 700 | 0.0004 | 1.2422 |
|
| 61 |
+
| 0.0003 | 266.67 | 800 | 0.0003 | 1.2422 |
|
| 62 |
+
| 0.0003 | 300.0 | 900 | 0.0003 | 1.2422 |
|
| 63 |
+
| 0.0003 | 333.33 | 1000 | 0.0003 | 1.2422 |
|
| 64 |
+
|
| 65 |
|
| 66 |
### Framework versions
|
| 67 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 290401888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05b4594d793f2f1e9ce21e71db7d80799da63426c9e0f93b35b90886224a0486
|
| 3 |
size 290401888
|