Automatic Speech Recognition
Transformers
Safetensors
Amharic
wav2vec2-bert
amharic
speech-recognition
ctc
leyu
Instructions to use caesar-abrham/Chaka-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use caesar-abrham/Chaka-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="caesar-abrham/Chaka-ASR")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("caesar-abrham/Chaka-ASR") model = AutoModelForCTC.from_pretrained("caesar-abrham/Chaka-ASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add Chaka-ASR model card, inference example, and upstream credits
Browse files
LICENSE
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Chaka-ASR
|
| 2 |
+
Creative Commons Attribution 4.0 International (CC BY 4.0)
|
| 3 |
+
|
| 4 |
+
Chaka-ASR is licensed under CC BY 4.0.
|
| 5 |
+
License: https://creativecommons.org/licenses/by/4.0/
|
| 6 |
+
Full legal terms: https://creativecommons.org/licenses/by/4.0/legalcode
|
| 7 |
+
|
| 8 |
+
Attribution: caesar-abrham, Chaka-ASR (2026)
|
| 9 |
+
https://huggingface.co/caesar-abrham/Chaka-ASR
|
| 10 |
+
|
| 11 |
+
Retain upstream attribution in NOTICE.md when sharing this model.
|
NOTICE.md
CHANGED
|
@@ -2,6 +2,6 @@
|
|
| 2 |
|
| 3 |
Chaka-ASR is fine-tuned from badrex/Ethio-ASR-amharic, which declares CC BY 4.0, and builds on facebook/w2v-bert-2.0.
|
| 4 |
|
| 5 |
-
Adaptation used Leyu Amharic speech datasets with WAXAL replay. Consult upstream model cards and dataset terms for attribution and applicable conditions.
|
| 6 |
|
| 7 |
-
|
|
|
|
| 2 |
|
| 3 |
Chaka-ASR is fine-tuned from badrex/Ethio-ASR-amharic, which declares CC BY 4.0, and builds on facebook/w2v-bert-2.0.
|
| 4 |
|
| 5 |
+
Adaptation used [Leyu Amharic speech datasets](https://huggingface.co/leyu-amharic) with WAXAL replay. Consult upstream model cards and dataset terms for attribution and applicable conditions.
|
| 6 |
|
| 7 |
+
Chaka-ASR is released under CC BY 4.0. See LICENSE for the license reference. This notice records upstream attribution.
|
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- am
|
|
|
|
| 4 |
library_name: transformers
|
| 5 |
pipeline_tag: automatic-speech-recognition
|
| 6 |
base_model: badrex/Ethio-ASR-amharic
|
|
@@ -93,12 +94,14 @@ Chaka-ASR acknowledges:
|
|
| 93 |
|
| 94 |
- [Ethio-ASR](https://huggingface.co/collections/badrex/ethio-asr), including the Amharic starting checkpoint.
|
| 95 |
- [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0), the upstream architecture and pretrained model.
|
| 96 |
-
- Leyu Amharic speech datasets used for adaptation.
|
| 97 |
- [WAXAL](https://huggingface.co/datasets/google/WaxalNLP), used as replay data during adaptation.
|
| 98 |
|
| 99 |
## License
|
| 100 |
|
| 101 |
-
|
|
|
|
|
|
|
| 102 |
|
| 103 |
## Feedback
|
| 104 |
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- am
|
| 4 |
+
license: cc-by-4.0
|
| 5 |
library_name: transformers
|
| 6 |
pipeline_tag: automatic-speech-recognition
|
| 7 |
base_model: badrex/Ethio-ASR-amharic
|
|
|
|
| 94 |
|
| 95 |
- [Ethio-ASR](https://huggingface.co/collections/badrex/ethio-asr), including the Amharic starting checkpoint.
|
| 96 |
- [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0), the upstream architecture and pretrained model.
|
| 97 |
+
- [Leyu Amharic speech datasets](https://huggingface.co/leyu-amharic), used for adaptation.
|
| 98 |
- [WAXAL](https://huggingface.co/datasets/google/WaxalNLP), used as replay data during adaptation.
|
| 99 |
|
| 100 |
## License
|
| 101 |
|
| 102 |
+
Chaka-ASR is released under the [Creative Commons Attribution 4.0 International license (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/).
|
| 103 |
+
|
| 104 |
+
You may share and adapt the model, including for commercial use, provided you give appropriate credit, link to the license, and indicate any changes. See [LICENSE](LICENSE) for the license reference and full terms.
|
| 105 |
|
| 106 |
## Feedback
|
| 107 |
|