Commit
•
b3482e9
1
Parent(s):
f8ac98d
add files
Browse files- README.md +14 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: sv
|
| 3 |
+
tags:
|
| 4 |
+
- audio
|
| 5 |
+
- automatic-speech-recognition
|
| 6 |
+
- voxpopuli
|
| 7 |
+
license: apache-2.0
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Wav2Vec2-Large-VoxPopuli
|
| 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 **sv** 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 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"apply_spec_augment": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Wav2Vec2Model"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"conv_bias": true,
|
| 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": true,
|
| 40 |
+
"eos_token_id": 2,
|
| 41 |
+
"feat_extract_activation": "gelu",
|
| 42 |
+
"feat_extract_dropout": 0.0,
|
| 43 |
+
"feat_extract_norm": "layer",
|
| 44 |
+
"feat_proj_dropout": 0.1,
|
| 45 |
+
"final_dropout": 0.0,
|
| 46 |
+
"gradient_checkpointing": false,
|
| 47 |
+
"hidden_act": "gelu",
|
| 48 |
+
"hidden_dropout": 0.1,
|
| 49 |
+
"hidden_size": 1024,
|
| 50 |
+
"initializer_range": 0.02,
|
| 51 |
+
"intermediate_size": 4096,
|
| 52 |
+
"layer_norm_eps": 1e-05,
|
| 53 |
+
"layerdrop": 0.1,
|
| 54 |
+
"mask_channel_length": 10,
|
| 55 |
+
"mask_channel_min_space": 1,
|
| 56 |
+
"mask_channel_other": 0.0,
|
| 57 |
+
"mask_channel_prob": 0.0,
|
| 58 |
+
"mask_channel_selection": "static",
|
| 59 |
+
"mask_feature_length": 10,
|
| 60 |
+
"mask_feature_prob": 0.0,
|
| 61 |
+
"mask_time_length": 10,
|
| 62 |
+
"mask_time_min_space": 1,
|
| 63 |
+
"mask_time_other": 0.0,
|
| 64 |
+
"mask_time_prob": 0.075,
|
| 65 |
+
"mask_time_selection": "static",
|
| 66 |
+
"model_type": "wav2vec2",
|
| 67 |
+
"num_attention_heads": 16,
|
| 68 |
+
"num_conv_pos_embedding_groups": 16,
|
| 69 |
+
"num_conv_pos_embeddings": 128,
|
| 70 |
+
"num_feat_extract_layers": 7,
|
| 71 |
+
"num_hidden_layers": 24,
|
| 72 |
+
"pad_token_id": 0,
|
| 73 |
+
"transformers_version": "4.6.0.dev0",
|
| 74 |
+
"vocab_size": 32
|
| 75 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e00a85284dd3fb3adc5b29e5d1652c74f77e903929caa3e1ddbe0124d31d059
|
| 3 |
+
size 1261920069
|