End of training
Browse files- README.md +8 -18
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,24 +1,24 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-small
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
-
|
| 7 |
-
-
|
| 8 |
model-index:
|
| 9 |
-
- name:
|
| 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 |
-
#
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.4159
|
| 21 |
-
- Wer: 84.5831
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -49,16 +49,6 @@ The following hyperparameters were used during training:
|
|
| 49 |
- training_steps: 4000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 56 |
-
| 0.4947 | 1.45 | 1000 | 0.3913 | 80.2040 |
|
| 57 |
-
| 0.2744 | 2.91 | 2000 | 0.3849 | 81.1038 |
|
| 58 |
-
| 0.1356 | 4.36 | 3000 | 0.4072 | 87.0026 |
|
| 59 |
-
| 0.0899 | 5.82 | 4000 | 0.4159 | 84.5831 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.36.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- hi
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: openai/whisper-small
|
| 6 |
tags:
|
| 7 |
+
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- mozilla-foundation/common_voice_11_0
|
| 11 |
model-index:
|
| 12 |
+
- name: Whisper Small Hi - Chinese
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
+
# Whisper Small Hi - Chinese
|
| 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 |
|
|
|
|
| 49 |
- training_steps: 4000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.36.0.dev0
|
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 sha256:1d7734884874f1a1513ed9aa760a4f8e97aaa02fd6d93a3a85d27b2ae9ca596b
|
| 3 |
size 966995080
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9803e108521ff927c37849b16d40d290e90c4d4a8cf2291db584f5ab388d15c
|
| 3 |
size 4856
|