Automatic Speech Recognition
Transformers
Karbi
wav2vec2
audio
speech
ctc
mms
low-resource
karbi
Eval Results (legacy)
Instructions to use sulabhkatiyar/ne-asr-mjw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sulabhkatiyar/ne-asr-mjw with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sulabhkatiyar/ne-asr-mjw")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("sulabhkatiyar/ne-asr-mjw") model = AutoModelForCTC.from_pretrained("sulabhkatiyar/ne-asr-mjw", device_map="auto") - Notebooks
- Google Colab
- Kaggle
phase-e3: upload tokenizer_config.json
Browse files- tokenizer_config.json +61 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"24": {
|
| 4 |
+
"content": "|",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"25": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"26": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"27": {
|
| 28 |
+
"content": "<s>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"28": {
|
| 36 |
+
"content": "</s>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": true,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"additional_special_tokens": null,
|
| 45 |
+
"backend": "custom",
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"is_local": true,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"model_specific_special_tokens": {
|
| 52 |
+
"word_delimiter_token": "|"
|
| 53 |
+
},
|
| 54 |
+
"pad_token": "[PAD]",
|
| 55 |
+
"processor_class": "Wav2Vec2Processor",
|
| 56 |
+
"replace_word_delimiter_char": " ",
|
| 57 |
+
"target_lang": null,
|
| 58 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 59 |
+
"unk_token": "[UNK]",
|
| 60 |
+
"word_delimiter_token": "|"
|
| 61 |
+
}
|