End of training
Browse files- README.md +36 -4
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,21 +1,43 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/neuronbit-tech/hindi-finetune-whisper-small/runs/a17oxlp9)
|
| 16 |
-
#
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -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 4.45.2
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- hi
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: openai/whisper-small
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- mozilla-foundation/common_voice_11_0
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
+
- name: Whisper Small Hi
|
| 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_11_0
|
| 22 |
+
config: hi
|
| 23 |
+
split: None
|
| 24 |
+
args: 'config: hi, split: test'
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 32.485397443494456
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
|
| 34 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/neuronbit-tech/hindi-finetune-whisper-small/runs/a17oxlp9)
|
| 35 |
+
# Whisper Small Hi
|
| 36 |
|
| 37 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
|
| 38 |
+
It achieves the following results on the evaluation set:
|
| 39 |
+
- Loss: 0.4390
|
| 40 |
+
- Wer: 32.4854
|
| 41 |
|
| 42 |
## Model description
|
| 43 |
|
|
|
|
| 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 |
+
| 0.0922 | 2.4450 | 1000 | 0.2977 | 35.0038 |
|
| 74 |
+
| 0.0209 | 4.8900 | 2000 | 0.3548 | 34.0430 |
|
| 75 |
+
| 0.0013 | 7.3350 | 3000 | 0.4121 | 32.3584 |
|
| 76 |
+
| 0.0004 | 9.7800 | 4000 | 0.4390 | 32.4854 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.45.2
|
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:b532523ef63ab4b62a0318c228d2e2333aadde0eaa658c36be111db7c607d055
|
| 3 |
size 966995080
|