patrickvonplaten commited on
Commit
003c1ff
1 Parent(s): 550f350
Files changed (3) hide show
  1. README.md +14 -0
  2. config.json +68 -0
  3. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: 10k
3
+ tags:
4
+ - audio
5
+ - automatic-speech-recognition
6
+ - voxpopuli
7
+ license: apache-2.0
8
+ ---
9
+
10
+ # Wav2Vec2-Base-VoxPopuli
11
+
12
+ [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) base model pretrained on the **10k** subset of [VoxPopuli corpus](https://arxiv.org/abs/2101.00390).
13
+
14
+ See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/tree/add_vp_asr)
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2Model"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "conv_bias": false,
10
+ "conv_dim": [
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512
18
+ ],
19
+ "conv_kernel": [
20
+ 10,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 2,
26
+ 2
27
+ ],
28
+ "conv_stride": [
29
+ 5,
30
+ 2,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2
36
+ ],
37
+ "ctc_loss_reduction": "sum",
38
+ "ctc_zero_infinity": false,
39
+ "do_stable_layer_norm": false,
40
+ "eos_token_id": 2,
41
+ "feat_extract_activation": "gelu",
42
+ "feat_extract_dropout": 0.0,
43
+ "feat_extract_norm": "group",
44
+ "feat_proj_dropout": 0.1,
45
+ "final_dropout": 0.1,
46
+ "gradient_checkpointing": false,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_dropout_prob": 0.1,
50
+ "hidden_size": 768,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.1,
55
+ "mask_feature_length": 10,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_prob": 0.05,
59
+ "model_type": "wav2vec2",
60
+ "num_attention_heads": 12,
61
+ "num_conv_pos_embedding_groups": 16,
62
+ "num_conv_pos_embeddings": 128,
63
+ "num_feat_extract_layers": 7,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "transformers_version": "4.6.0.dev0",
67
+ "vocab_size": 32
68
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c70e65e0dc79375fc54b11a183441f2bc4f43a3fcdd768c4d857bfaefc344e
3
+ size 377569754