Commit
·
ec93be8
1
Parent(s):
0487521
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,17 +1,40 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
|
|
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
-
- name:
|
| 6 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
|
| 12 |
-
#
|
| 13 |
|
| 14 |
-
This model
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
@@ -42,6 +65,22 @@ The following hyperparameters were used during training:
|
|
| 42 |
- training_steps: 5000
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Framework versions
|
| 46 |
|
| 47 |
- Transformers 4.26.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ta
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
+
- whisper-event
|
| 7 |
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- mozilla-foundation/common_voice_11_0
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
model-index:
|
| 13 |
+
- name: Whisper Tiny ml - Bharat Ramanathan
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Common Voice 11.0
|
| 20 |
+
type: mozilla-foundation/common_voice_11_0
|
| 21 |
+
config: null
|
| 22 |
+
split: None
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Wer
|
| 25 |
+
type: wer
|
| 26 |
+
value: 58.75912408759124
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
|
| 32 |
+
# Whisper Tiny ml - Bharat Ramanathan
|
| 33 |
|
| 34 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.2636
|
| 37 |
+
- Wer: 58.7591
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 65 |
- training_steps: 5000
|
| 66 |
- mixed_precision_training: Native AMP
|
| 67 |
|
| 68 |
+
### Training results
|
| 69 |
+
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 72 |
+
| 0.5755 | 4.02 | 500 | 0.4241 | 81.2652 |
|
| 73 |
+
| 0.4182 | 9.01 | 1000 | 0.3245 | 72.7494 |
|
| 74 |
+
| 0.3387 | 14.01 | 1500 | 0.2914 | 67.2749 |
|
| 75 |
+
| 0.2923 | 19.0 | 2000 | 0.2745 | 60.3406 |
|
| 76 |
+
| 0.2596 | 24.0 | 2500 | 0.2645 | 58.2725 |
|
| 77 |
+
| 0.2356 | 28.02 | 3000 | 0.2629 | 60.3406 |
|
| 78 |
+
| 0.2167 | 33.01 | 3500 | 0.2647 | 59.9757 |
|
| 79 |
+
| 0.2039 | 4.02 | 4000 | 0.2617 | 58.2725 |
|
| 80 |
+
| 0.1938 | 9.01 | 4500 | 0.2644 | 58.2725 |
|
| 81 |
+
| 0.1858 | 14.01 | 5000 | 0.2636 | 58.7591 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
### Framework versions
|
| 85 |
|
| 86 |
- Transformers 4.26.0.dev0
|