Update with backwards compatible tokenizer format
Browse files
parakeet-tdt_ctc-110m/config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"nemo_model_type": "parakeet",
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"vocab_size": 1024,
|
| 7 |
+
}
|
parakeet-tdt_ctc-110m/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
parakeet-tdt_ctc-110m/tokenizer_config.json
CHANGED
|
@@ -22,6 +22,6 @@
|
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": "<pad>",
|
| 24 |
"processor_class": "ParakeetProcessor",
|
| 25 |
-
"tokenizer_class": "
|
| 26 |
"unk_token": "<unk>"
|
| 27 |
}
|
|
|
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": "<pad>",
|
| 24 |
"processor_class": "ParakeetProcessor",
|
| 25 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 26 |
"unk_token": "<unk>"
|
| 27 |
}
|