add files
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- rinna.png +0 -0
- spiece.model +3 -0
- spiece.vocab +0 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"NueASRModel"
|
4 |
+
],
|
5 |
+
"audio_encoder_config": {
|
6 |
+
"architectures": [
|
7 |
+
"HubertModel"
|
8 |
+
],
|
9 |
+
"model_type": "hubert",
|
10 |
+
"torch_dtype": "float16"
|
11 |
+
},
|
12 |
+
"bridge_conv_kernel_size": [
|
13 |
+
4,
|
14 |
+
4
|
15 |
+
],
|
16 |
+
"bridge_conv_stride": [
|
17 |
+
2,
|
18 |
+
2
|
19 |
+
],
|
20 |
+
"llm_config": {
|
21 |
+
"architectures": [
|
22 |
+
"GPTNeoXForCausalLM"
|
23 |
+
],
|
24 |
+
"attention_dropout": 0.1,
|
25 |
+
"bos_token_id": 2,
|
26 |
+
"eos_token_id": 3,
|
27 |
+
"hidden_dropout": 0.1,
|
28 |
+
"hidden_size": 2816,
|
29 |
+
"intermediate_size": 11264,
|
30 |
+
"model_type": "gpt_neox",
|
31 |
+
"num_attention_heads": 22,
|
32 |
+
"num_hidden_layers": 36,
|
33 |
+
"rotary_pct": 1.0,
|
34 |
+
"torch_dtype": "float16",
|
35 |
+
"use_parallel_residual": false,
|
36 |
+
"vocab_size": 32000
|
37 |
+
},
|
38 |
+
"model_type": "nue_asr",
|
39 |
+
"torch_dtype": "float16",
|
40 |
+
"transformers_version": "4.33.2"
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de717516ec86901ec73d4f9eb91104c71482c72b0f37b2e938629283692a4c31
|
3 |
+
size 7417241633
|
rinna.png
ADDED
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9da51f3764f2cd72060e6e3edc460beae0aa32b12a9664d6d5b2aed274d2146
|
3 |
+
size 786149
|
spiece.vocab
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": false, "tokenizer_class": "T5Tokenizer"}
|