Upload processor
Browse files- processor_config.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
processor_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor": {
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"feature_extractor_type": "OmniASRFeatureExtractor",
|
| 5 |
+
"feature_size": 1,
|
| 6 |
+
"padding_side": "right",
|
| 7 |
+
"padding_value": 0,
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
},
|
| 11 |
+
"processor_class": "OmniASRCTCProcessor"
|
| 12 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding": true,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"processor_class": "OmniASRCTCProcessor",
|
| 11 |
+
"return_tensors": "pt",
|
| 12 |
+
"tokenizer_class": "ParakeetTokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|