Automatic Speech Recognition
Transformers
Safetensors
Adioukrou
wav2vec2
adja
asr
speech-recognition
low-resource
xls-r
cs-thesis-may-2026
Instructions to use JosueG/wav2vec2-xlsr-adja-c4v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JosueG/wav2vec2-xlsr-adja-c4v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="JosueG/wav2vec2-xlsr-adja-c4v2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("JosueG/wav2vec2-xlsr-adja-c4v2") model = AutoModelForCTC.from_pretrained("JosueG/wav2vec2-xlsr-adja-c4v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Publish C4v2 (XLS-R CTC) with reconstructed tokenizer for serverless inference
Browse files- special_tokens_map.json +3 -0
- tokenizer_config.json +3 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"pad_token": "<blank>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<pad>"
|
| 4 |
+
],
|
| 5 |
"bos_token": "<s>",
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"pad_token": "<blank>",
|
tokenizer_config.json
CHANGED
|
@@ -41,6 +41,9 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
|
|
|
|
|
|
| 44 |
"bos_token": "<s>",
|
| 45 |
"clean_up_tokenization_spaces": false,
|
| 46 |
"do_lower_case": false,
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"additional_special_tokens": [
|
| 45 |
+
"<pad>"
|
| 46 |
+
],
|
| 47 |
"bos_token": "<s>",
|
| 48 |
"clean_up_tokenization_spaces": false,
|
| 49 |
"do_lower_case": false,
|