Automatic Speech Recognition
Transformers
PyTorch
Malayalam
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use parambharat/whisper-tiny-ml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use parambharat/whisper-tiny-ml with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="parambharat/whisper-tiny-ml")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("parambharat/whisper-tiny-ml") model = AutoModelForSpeechSeq2Seq.from_pretrained("parambharat/whisper-tiny-ml", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
b187200
1
Parent(s): f230530
update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- eval_loss: 0.
|
| 17 |
-
- eval_wer:
|
| 18 |
-
- eval_runtime:
|
| 19 |
-
- eval_samples_per_second: 1.
|
| 20 |
-
- eval_steps_per_second: 0.
|
| 21 |
- epoch: 4.02
|
| 22 |
- step: 500
|
| 23 |
|
|
@@ -53,6 +53,6 @@ The following hyperparameters were used during training:
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.26.0.dev0
|
| 56 |
-
- Pytorch 1.13.0
|
| 57 |
- Datasets 2.7.1.dev0
|
| 58 |
- Tokenizers 0.13.2
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- eval_loss: 0.4241
|
| 17 |
+
- eval_wer: 81.2652
|
| 18 |
+
- eval_runtime: 53.1129
|
| 19 |
+
- eval_samples_per_second: 1.883
|
| 20 |
+
- eval_steps_per_second: 0.132
|
| 21 |
- epoch: 4.02
|
| 22 |
- step: 500
|
| 23 |
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.26.0.dev0
|
| 56 |
+
- Pytorch 1.13.0
|
| 57 |
- Datasets 2.7.1.dev0
|
| 58 |
- Tokenizers 0.13.2
|