Automatic Speech Recognition
Transformers
Safetensors
Hausa
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use EYEDOL/whisper-tiny-hausa2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EYEDOL/whisper-tiny-hausa2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="EYEDOL/whisper-tiny-hausa2")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("EYEDOL/whisper-tiny-hausa2") model = AutoModelForSpeechSeq2Seq.from_pretrained("EYEDOL/whisper-tiny-hausa2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -1,22 +1,36 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: EYEDOL/whisper-tiny-hausa1
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
-
- name: whisper-tiny-hausa2
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
# whisper-tiny-hausa2
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [EYEDOL/whisper-tiny-hausa1](https://huggingface.co/EYEDOL/whisper-tiny-hausa1) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6946
|
| 22 |
- Wer Ortho: 0.5454
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- ha
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: EYEDOL/whisper-tiny-hausa1
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- EYEDOL/naija-voices-hausa-split_0-5
|
| 11 |
metrics:
|
| 12 |
- wer
|
| 13 |
model-index:
|
| 14 |
+
- name: EYEDOL/whisper-tiny-hausa2
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: EYEDOL/naija-voices-hausa-split_0-5
|
| 21 |
+
type: EYEDOL/naija-voices-hausa-split_0-5
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.48092983669344114
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
|
| 31 |
+
# EYEDOL/whisper-tiny-hausa2
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [EYEDOL/whisper-tiny-hausa1](https://huggingface.co/EYEDOL/whisper-tiny-hausa1) on the EYEDOL/naija-voices-hausa-split_0-5 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.6946
|
| 36 |
- Wer Ortho: 0.5454
|