Commit
•
df76731
1
Parent(s):
309997b
update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,24 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- fleurs
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: openai/whisper-tiny
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# openai/whisper-tiny
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -34,15 +52,31 @@ More information needed
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 1e-05
|
| 37 |
-
- train_batch_size:
|
| 38 |
-
- eval_batch_size:
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- lr_scheduler_warmup_ratio: 0.
|
| 43 |
-
- training_steps:
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.26.0.dev0
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- fleurs
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
model-index:
|
| 10 |
- name: openai/whisper-tiny
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: fleurs
|
| 17 |
+
type: fleurs
|
| 18 |
+
config: en_us
|
| 19 |
+
split: validation
|
| 20 |
+
args: en_us
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 19.3465805193222
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
# openai/whisper-tiny
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.5568
|
| 35 |
+
- Wer: 19.3466
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 52 |
|
| 53 |
The following hyperparameters were used during training:
|
| 54 |
- learning_rate: 1e-05
|
| 55 |
+
- train_batch_size: 64
|
| 56 |
+
- eval_batch_size: 32
|
| 57 |
- seed: 42
|
| 58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 61 |
+
- training_steps: 407
|
| 62 |
- mixed_precision_training: Native AMP
|
| 63 |
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 68 |
+
| 1.1599 | 0.1 | 40 | 1.1427 | 15.2139 |
|
| 69 |
+
| 0.4655 | 1.1 | 80 | 0.5613 | 17.5911 |
|
| 70 |
+
| 0.2753 | 2.09 | 120 | 0.5241 | 17.2132 |
|
| 71 |
+
| 0.2077 | 3.09 | 160 | 0.5242 | 17.2620 |
|
| 72 |
+
| 0.1636 | 4.09 | 200 | 0.5290 | 17.6643 |
|
| 73 |
+
| 0.1322 | 5.09 | 240 | 0.5351 | 18.2128 |
|
| 74 |
+
| 0.123 | 6.08 | 280 | 0.5429 | 18.9077 |
|
| 75 |
+
| 0.1074 | 7.08 | 320 | 0.5500 | 19.0540 |
|
| 76 |
+
| 0.1007 | 8.08 | 360 | 0.5553 | 19.3100 |
|
| 77 |
+
| 0.0876 | 9.08 | 400 | 0.5568 | 19.3466 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
### Framework versions
|
| 81 |
|
| 82 |
- Transformers 4.26.0.dev0
|