Instructions to use confit/wav2vec2-base-spkreg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use confit/wav2vec2-base-spkreg with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="confit/wav2vec2-base-spkreg", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("confit/wav2vec2-base-spkreg", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload config
Browse files- config.json +3 -7
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/wav2vec2-base",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"adapter_attn_dim": null,
|
| 5 |
"adapter_kernel_size": 3,
|
|
@@ -7,14 +6,11 @@
|
|
| 7 |
"add_adapter": false,
|
| 8 |
"apply_spec_augment": true,
|
| 9 |
"architectures": [
|
| 10 |
-
"
|
| 11 |
],
|
| 12 |
"attention_dropout": 0.1,
|
| 13 |
"auto_map": {
|
| 14 |
-
"AutoConfig": "configuration_wav2vec2_spkreg.Wav2Vec2SpkRegConfig"
|
| 15 |
-
"AutoFeatureExtractor": "feature_extractor_wav2vec2_spkreg.Wav2Vec2SpkRegFeatureExtractor",
|
| 16 |
-
"AutoModel": "modeling_wav2vec2_spkreg.Wav2Vec2SpkRegModel",
|
| 17 |
-
"AutoModelForAudioClassification": "modeling_wav2vec2_spkreg.Wav2Vec2SpkRegForSequenceClassification"
|
| 18 |
},
|
| 19 |
"bos_token_id": 1,
|
| 20 |
"classifier_proj_size": 256,
|
|
@@ -60,6 +56,7 @@
|
|
| 60 |
"feat_quantizer_dropout": 0.0,
|
| 61 |
"final_dropout": 0.0,
|
| 62 |
"freeze_feat_extract_train": true,
|
|
|
|
| 63 |
"hidden_act": "gelu",
|
| 64 |
"hidden_dropout": 0.1,
|
| 65 |
"hidden_size": 768,
|
|
@@ -122,7 +119,6 @@
|
|
| 122 |
1,
|
| 123 |
1
|
| 124 |
],
|
| 125 |
-
"torch_dtype": "float32",
|
| 126 |
"transformers_version": "4.46.2",
|
| 127 |
"use_weighted_layer_sum": false,
|
| 128 |
"vocab_size": 32,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"adapter_attn_dim": null,
|
| 4 |
"adapter_kernel_size": 3,
|
|
|
|
| 6 |
"add_adapter": false,
|
| 7 |
"apply_spec_augment": true,
|
| 8 |
"architectures": [
|
| 9 |
+
"Wav2Vec2ForPreTraining"
|
| 10 |
],
|
| 11 |
"attention_dropout": 0.1,
|
| 12 |
"auto_map": {
|
| 13 |
+
"AutoConfig": "configuration_wav2vec2_spkreg.Wav2Vec2SpkRegConfig"
|
|
|
|
|
|
|
|
|
|
| 14 |
},
|
| 15 |
"bos_token_id": 1,
|
| 16 |
"classifier_proj_size": 256,
|
|
|
|
| 56 |
"feat_quantizer_dropout": 0.0,
|
| 57 |
"final_dropout": 0.0,
|
| 58 |
"freeze_feat_extract_train": true,
|
| 59 |
+
"gradient_checkpointing": true,
|
| 60 |
"hidden_act": "gelu",
|
| 61 |
"hidden_dropout": 0.1,
|
| 62 |
"hidden_size": 768,
|
|
|
|
| 119 |
1,
|
| 120 |
1
|
| 121 |
],
|
|
|
|
| 122 |
"transformers_version": "4.46.2",
|
| 123 |
"use_weighted_layer_sum": false,
|
| 124 |
"vocab_size": 32,
|