End of training
Browse files- README.md +27 -2
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -8,9 +8,24 @@ tags:
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_17_0
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: Whisper Tiny Nepali
|
| 13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# Whisper Tiny Nepali
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,11 +64,18 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 500
|
| 49 |
-
- training_steps:
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_17_0
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
- name: Whisper Tiny Nepali
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: Common Voice 17.0
|
| 21 |
+
type: mozilla-foundation/common_voice_17_0
|
| 22 |
+
config: ne-NP
|
| 23 |
+
split: test
|
| 24 |
+
args: 'config: ne-NP, split: train+validation'
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 81.72804532577904
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
# Whisper Tiny Nepali
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 1.5772
|
| 39 |
+
- Wer: 81.7280
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 64 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 65 |
- lr_scheduler_type: linear
|
| 66 |
- lr_scheduler_warmup_steps: 500
|
| 67 |
+
- training_steps: 5000
|
| 68 |
- mixed_precision_training: Native AMP
|
| 69 |
|
| 70 |
### Training results
|
| 71 |
|
| 72 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 73 |
+
|:-------------:|:--------:|:----:|:---------------:|:-------:|
|
| 74 |
+
| 0.0042 | 32.2623 | 1000 | 1.1940 | 81.7280 |
|
| 75 |
+
| 0.0002 | 64.5246 | 2000 | 1.4012 | 81.3739 |
|
| 76 |
+
| 0.0001 | 96.7869 | 3000 | 1.4975 | 82.0822 |
|
| 77 |
+
| 0.0001 | 129.0328 | 4000 | 1.5517 | 81.8697 |
|
| 78 |
+
| 0.0001 | 161.2951 | 5000 | 1.5772 | 81.7280 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 151061672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51ac2c8e33d679067ed540a55281cbe59e944595def1117b700fc8903ebaa71b
|
| 3 |
size 151061672
|