Upload tokenizer
Browse files- README.md +6 -6
- tokenizer_config.json +0 -1
README.md
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
base_model: facebook/w2v-bert-2.0
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- common_voice_16_0
|
|
|
|
| 8 |
metrics:
|
| 9 |
- wer
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: w2v-bert-2.0-mongolian-colab-CV16.0
|
| 12 |
results:
|
| 13 |
- task:
|
| 14 |
-
name: Automatic Speech Recognition
|
| 15 |
type: automatic-speech-recognition
|
|
|
|
| 16 |
dataset:
|
| 17 |
name: common_voice_16_0
|
| 18 |
type: common_voice_16_0
|
|
@@ -20,9 +20,9 @@ model-index:
|
|
| 20 |
split: test
|
| 21 |
args: mn
|
| 22 |
metrics:
|
| 23 |
-
-
|
| 24 |
-
type: wer
|
| 25 |
value: 0.3243419621492278
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: facebook/w2v-bert-2.0
|
|
|
|
|
|
|
| 3 |
datasets:
|
| 4 |
- common_voice_16_0
|
| 5 |
+
license: mit
|
| 6 |
metrics:
|
| 7 |
- wer
|
| 8 |
+
tags:
|
| 9 |
+
- generated_from_trainer
|
| 10 |
model-index:
|
| 11 |
- name: w2v-bert-2.0-mongolian-colab-CV16.0
|
| 12 |
results:
|
| 13 |
- task:
|
|
|
|
| 14 |
type: automatic-speech-recognition
|
| 15 |
+
name: Automatic Speech Recognition
|
| 16 |
dataset:
|
| 17 |
name: common_voice_16_0
|
| 18 |
type: common_voice_16_0
|
|
|
|
| 20 |
split: test
|
| 21 |
args: mn
|
| 22 |
metrics:
|
| 23 |
+
- type: wer
|
|
|
|
| 24 |
value: 0.3243419621492278
|
| 25 |
+
name: Wer
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
tokenizer_config.json
CHANGED
|
@@ -39,7 +39,6 @@
|
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
| 42 |
-
"processor_class": "Wav2Vec2BertProcessor",
|
| 43 |
"replace_word_delimiter_char": " ",
|
| 44 |
"target_lang": null,
|
| 45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
"pad_token": "[PAD]",
|
|
|
|
| 42 |
"replace_word_delimiter_char": " ",
|
| 43 |
"target_lang": null,
|
| 44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|