hf-transformers-bot
commited on
Commit
·
83f9756
1
Parent(s):
54e691e
Upload tiny models for Speech2TextModel
Browse files- config.json +43 -0
- preprocessor_config.json +12 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +6 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiny_models/speech_to_text/Speech2TextModel",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"Speech2TextModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"conv_channels": 32,
|
11 |
+
"conv_kernel_sizes": [
|
12 |
+
5,
|
13 |
+
5
|
14 |
+
],
|
15 |
+
"d_model": 16,
|
16 |
+
"decoder_attention_heads": 4,
|
17 |
+
"decoder_ffn_dim": 4,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 2,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 4,
|
23 |
+
"encoder_ffn_dim": 4,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 2,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"init_std": 0.02,
|
28 |
+
"input_channels": 1,
|
29 |
+
"input_feat_per_channel": 24,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"max_position_embeddings": 20,
|
32 |
+
"max_source_positions": 20,
|
33 |
+
"max_target_positions": 20,
|
34 |
+
"model_type": "speech_to_text",
|
35 |
+
"num_conv_layers": 2,
|
36 |
+
"num_hidden_layers": 2,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"scale_embedding": true,
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.28.0.dev0",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 10000
|
43 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_ceptral_normalize": true,
|
3 |
+
"feature_extractor_type": "Speech2TextFeatureExtractor",
|
4 |
+
"feature_size": 24,
|
5 |
+
"normalize_means": true,
|
6 |
+
"normalize_vars": true,
|
7 |
+
"num_mel_bins": 24,
|
8 |
+
"padding_side": "right",
|
9 |
+
"padding_value": 0.0,
|
10 |
+
"return_attention_mask": true,
|
11 |
+
"sampling_rate": 16000
|
12 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:517096920c10767ea44acf566807d59fc9874f2c7f21b617cfbf84d3c0f5e8fb
|
3 |
+
size 728270
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:052a168787a9160b4b2ba54e4995e9600298812c34191ca3f70cea51cd4f5c1e
|
3 |
+
size 416684
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0b918426cae8bde3ede71814405c3379e8f4b0b7cbad048a75d9d16a9b6c945
|
3 |
+
size 809424
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"do_upper_case": false,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"lang_codes": null,
|
8 |
+
"model_max_length": 20,
|
9 |
+
"pad_token": "<pad>",
|
10 |
+
"sp_model_kwargs": {},
|
11 |
+
"special_tokens_map_file": "/home/suraj/.cache/huggingface/transformers/f39f1499e9c4d2b3e803e3cad8a31c4cf3e626e1c69197d4cd6921e5c07007f9.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
|
12 |
+
"tgt_lang": null,
|
13 |
+
"tokenizer_class": "Speech2TextTokenizer",
|
14 |
+
"tokenizer_file": null,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|