Upload 6 files
Browse files- preprocessor_config.json +8 -0
- processor_config.json +3 -10
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -5
preprocessor_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 3 |
+
"sampling_rate": 16000,
|
| 4 |
+
"padding_value": 0.0,
|
| 5 |
+
"do_normalize": false,
|
| 6 |
+
"return_attention_mask": true,
|
| 7 |
+
"pad_to_multiple_of": 80
|
| 8 |
+
}
|
processor_config.json
CHANGED
|
@@ -1,12 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"feature_size": 1,
|
| 6 |
-
"padding_side": "right",
|
| 7 |
-
"padding_value": 0.0,
|
| 8 |
-
"return_attention_mask": true,
|
| 9 |
-
"sampling_rate": 16000
|
| 10 |
-
},
|
| 11 |
-
"processor_class": "Wav2Vec2Processor"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"processor_class": "MoonshineStreamingProcessor",
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3 |
+
"model_max_length": 4096,
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"pad_token": "<unk>"
|
| 8 |
}
|