Commit
•
4771df5
1
Parent(s):
49b3629
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,41 +1,28 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- ta
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
-
- whisper-event
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
-
metrics:
|
| 11 |
-
- wer
|
| 12 |
model-index:
|
| 13 |
-
- name:
|
| 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: default
|
| 22 |
-
split: test
|
| 23 |
-
args: default
|
| 24 |
-
metrics:
|
| 25 |
-
- name: Wer
|
| 26 |
-
type: wer
|
| 27 |
-
value: 31.399708853500375
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 31 |
should probably proofread and complete it, then remove this comment. -->
|
| 32 |
|
| 33 |
-
#
|
| 34 |
|
| 35 |
-
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
-
-
|
| 38 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
@@ -63,20 +50,9 @@ The following hyperparameters were used during training:
|
|
| 63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 64 |
- lr_scheduler_type: linear
|
| 65 |
- lr_scheduler_warmup_steps: 1000
|
| 66 |
-
- training_steps:
|
| 67 |
- mixed_precision_training: Native AMP
|
| 68 |
|
| 69 |
-
### Training results
|
| 70 |
-
|
| 71 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 72 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 73 |
-
| 0.5622 | 0.2 | 1000 | 0.4460 | 41.4141 |
|
| 74 |
-
| 0.4151 | 0.4 | 2000 | 0.3657 | 35.1390 |
|
| 75 |
-
| 0.3727 | 0.6 | 3000 | 0.3417 | 33.1723 |
|
| 76 |
-
| 0.3519 | 0.8 | 4000 | 0.3252 | 31.9497 |
|
| 77 |
-
| 0.3354 | 1.0 | 5000 | 0.3192 | 31.3997 |
|
| 78 |
-
|
| 79 |
-
|
| 80 |
### Framework versions
|
| 81 |
|
| 82 |
- Transformers 4.26.0.dev0
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
+
- tamil_asr_corpus
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
+
- name: whisper-tiny-ta
|
| 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 |
+
# whisper-tiny-ta
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the tamil_asr_corpus dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.3283
|
| 20 |
+
- eval_wer: 31.6966
|
| 21 |
+
- eval_runtime: 3153.3863
|
| 22 |
+
- eval_samples_per_second: 3.745
|
| 23 |
+
- eval_steps_per_second: 0.234
|
| 24 |
+
- epoch: 0.1
|
| 25 |
+
- step: 6000
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
- lr_scheduler_warmup_steps: 1000
|
| 53 |
+
- training_steps: 10000
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.26.0.dev0
|