Commit
•
a7cc694
1
Parent(s):
01c6843
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,10 +18,10 @@ model-index:
|
|
| 18 |
args: ml
|
| 19 |
metrics:
|
| 20 |
- type: wer
|
| 21 |
-
value:
|
| 22 |
name: WER
|
| 23 |
- type: cer
|
| 24 |
-
value:
|
| 25 |
name: CER
|
| 26 |
library_name: transformers
|
| 27 |
---
|
|
@@ -36,12 +36,27 @@ The fine-tuned model on evaluating in the following dataset:
|
|
| 36 |
|
| 37 |
**In Mozilla CommonVoice 11.0 dataset (Malayalam subset):**
|
| 38 |
|
| 39 |
-
WER -
|
| 40 |
|
| 41 |
-
CER -
|
| 42 |
|
| 43 |
**In SMC Malayalam Speech Corpus dataset:**
|
| 44 |
|
| 45 |
-
WER -
|
| 46 |
|
| 47 |
-
CER -
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
args: ml
|
| 19 |
metrics:
|
| 20 |
- type: wer
|
| 21 |
+
value: 61.84
|
| 22 |
name: WER
|
| 23 |
- type: cer
|
| 24 |
+
value: 15.41
|
| 25 |
name: CER
|
| 26 |
library_name: transformers
|
| 27 |
---
|
|
|
|
| 36 |
|
| 37 |
**In Mozilla CommonVoice 11.0 dataset (Malayalam subset):**
|
| 38 |
|
| 39 |
+
WER - 61.84
|
| 40 |
|
| 41 |
+
CER - 15.41
|
| 42 |
|
| 43 |
**In SMC Malayalam Speech Corpus dataset:**
|
| 44 |
|
| 45 |
+
WER - 70.49
|
| 46 |
|
| 47 |
+
CER - 17.0
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
## Training
|
| 51 |
+
|
| 52 |
+
[Script Used for training](https://github.com/kurianbenoy/Keyword_generator_project/blob/main/Whisper_IMASC_final_e2eofficerun.ipynb)
|
| 53 |
+
|
| 54 |
+
[Training run](https://wandb.ai/hello34/wandb_whisper_e2e/runs/q2xlvbw5)
|
| 55 |
+
|
| 56 |
+
[Experiment Tracking with Weights and Biases](https://wandb.ai/hello34/wandb_whisper_e2e)
|
| 57 |
+
|
| 58 |
+
- GPUs used: A100 and 80 GB
|
| 59 |
+
|
| 60 |
+
- Training Time: 16 hours
|
| 61 |
+
|
| 62 |
+
- This project was build with A100 80GB GPU provided by [E2E during their open hack day](https://www.eventbrite.com/e/open-hack-day-tickets-783582435157)
|