Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Urdu
wav2vec2
hf-asr-leaderboard
robust-speech-event
Eval Results (legacy)
Instructions to use kingabzpro/wav2vec2-60-urdu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kingabzpro/wav2vec2-60-urdu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kingabzpro/wav2vec2-60-urdu")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("kingabzpro/wav2vec2-60-urdu") model = AutoModelForCTC.from_pretrained("kingabzpro/wav2vec2-60-urdu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
899f9ed
1
Parent(s): 73e8d12
Training in progress, step 40
Browse files
config.json
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 3 |
"activation_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 4 |
"apply_spec_augment": true,
|
| 5 |
"architectures": [
|
| 6 |
"Wav2Vec2ForCTC"
|
|
@@ -63,13 +66,16 @@
|
|
| 63 |
"mask_channel_prob": 0.0,
|
| 64 |
"mask_channel_selection": "static",
|
| 65 |
"mask_feature_length": 10,
|
|
|
|
| 66 |
"mask_feature_prob": 0.0,
|
| 67 |
"mask_time_length": 10,
|
|
|
|
| 68 |
"mask_time_min_space": 1,
|
| 69 |
"mask_time_other": 0.0,
|
| 70 |
"mask_time_prob": 0.05,
|
| 71 |
"mask_time_selection": "static",
|
| 72 |
"model_type": "wav2vec2",
|
|
|
|
| 73 |
"num_attention_heads": 16,
|
| 74 |
"num_codevector_groups": 2,
|
| 75 |
"num_codevectors_per_group": 320,
|
|
@@ -78,10 +84,33 @@
|
|
| 78 |
"num_feat_extract_layers": 7,
|
| 79 |
"num_hidden_layers": 24,
|
| 80 |
"num_negatives": 100,
|
|
|
|
| 81 |
"pad_token_id": 47,
|
| 82 |
"proj_codevector_dim": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
"torch_dtype": "float32",
|
| 84 |
-
"transformers_version": "4.
|
| 85 |
"use_weighted_layer_sum": false,
|
| 86 |
-
"vocab_size": 50
|
|
|
|
| 87 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
"apply_spec_augment": true,
|
| 8 |
"architectures": [
|
| 9 |
"Wav2Vec2ForCTC"
|
|
|
|
| 66 |
"mask_channel_prob": 0.0,
|
| 67 |
"mask_channel_selection": "static",
|
| 68 |
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
"mask_feature_prob": 0.0,
|
| 71 |
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
"mask_time_min_space": 1,
|
| 74 |
"mask_time_other": 0.0,
|
| 75 |
"mask_time_prob": 0.05,
|
| 76 |
"mask_time_selection": "static",
|
| 77 |
"model_type": "wav2vec2",
|
| 78 |
+
"num_adapter_layers": 3,
|
| 79 |
"num_attention_heads": 16,
|
| 80 |
"num_codevector_groups": 2,
|
| 81 |
"num_codevectors_per_group": 320,
|
|
|
|
| 84 |
"num_feat_extract_layers": 7,
|
| 85 |
"num_hidden_layers": 24,
|
| 86 |
"num_negatives": 100,
|
| 87 |
+
"output_hidden_size": 1024,
|
| 88 |
"pad_token_id": 47,
|
| 89 |
"proj_codevector_dim": 768,
|
| 90 |
+
"tdnn_dilation": [
|
| 91 |
+
1,
|
| 92 |
+
2,
|
| 93 |
+
3,
|
| 94 |
+
1,
|
| 95 |
+
1
|
| 96 |
+
],
|
| 97 |
+
"tdnn_dim": [
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
1500
|
| 103 |
+
],
|
| 104 |
+
"tdnn_kernel": [
|
| 105 |
+
5,
|
| 106 |
+
3,
|
| 107 |
+
3,
|
| 108 |
+
1,
|
| 109 |
+
1
|
| 110 |
+
],
|
| 111 |
"torch_dtype": "float32",
|
| 112 |
+
"transformers_version": "4.15.0",
|
| 113 |
"use_weighted_layer_sum": false,
|
| 114 |
+
"vocab_size": 50,
|
| 115 |
+
"xvector_output_dim": 512
|
| 116 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262128689
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6dcad711f186c16c91fb8d48a659d536327746349ac7b635aa0bb3f8572955a
|
| 3 |
size 1262128689
|
runs/Jan20_20-35-28_18132f059d04/1642710954.7284203/events.out.tfevents.1642710954.18132f059d04.74.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:042832186b5460720fbdb72835e803a4e65faf4ced598b81517a6e05709c23c6
|
| 3 |
+
size 4763
|
runs/Jan20_20-35-28_18132f059d04/events.out.tfevents.1642710954.18132f059d04.74.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:772f5ec45b61ac89431069bb6449c892026253f8dbdaf1f3e8455d549524aa76
|
| 3 |
+
size 5456
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b7d2bf069aab3b38203e650d057c886bb62c0fac16a6f6e57b82661309ce7fc
|
| 3 |
+
size 2927
|