patrickvonplaten commited on
Commit
04df3a9
1 Parent(s): 2a9fe71
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: hr
3
+ tags:
4
+ - audio
5
+ - automatic-speech-recognition
6
+ - voxpopuli
7
+ license: cc-by-nc-4.0
8
+ ---
9
+
10
+ # Wav2Vec2-Base-VoxPopuli-Finetuned
11
+
12
+ [Facebook's Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/) large model pretrained on the 10K unlabeled subset of [VoxPopuli corpus](https://arxiv.org/abs/2101.00390) and fine-tuned on the transcribed data in hr (refer to Table 1 of paper for more information).
13
+
14
+ **Paper**: *[VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation
15
+ Learning, Semi-Supervised Learning and Interpretation](https://arxiv.org/abs/2101.00390)*
16
+
17
+ **Authors**: *Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux* from *Facebook AI*
18
+
19
+ See the official website for more information, [here](https://github.com/facebookresearch/voxpopuli/)
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForCTC"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
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": 1,
66
+ "transformers_version": "4.6.0.dev0",
67
+ "vocab_size": 39
68
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5286a501690dd24494e3e3d18e83f47f30d3fec0c7104798d5bcc9dbcebc946
3
+ size 377694060
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "a": 5, "i": 6, "o": 7, "e": 8, "n": 9, "r": 10, "j": 11, "t": 12, "s": 13, "u": 14, "m": 15, "v": 16, "d": 17, "k": 18, "p": 19, "l": 20, "z": 21, "g": 22, "b": 23, "c": 24, "h": 25, "č": 26, "š": 27, "ž": 28, "ć": 29, "f": 30, "đ": 31, "w": 32, "y": 33, "x": 34, "q": 35, "ü": 36, "á": 37, "ö": 38}