Instructions to use Priyanship/outputs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Priyanship/outputs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Priyanship/outputs")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Priyanship/outputs") model = AutoModelForCTC.from_pretrained("Priyanship/outputs", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 2,084 Bytes
4d5c03c d44c8f6 4d5c03c d44c8f6 4d5c03c 565c0c9 4d5c03c 565c0c9 4d5c03c d44c8f6 4d5c03c 565c0c9 4d5c03c 565c0c9 57afd7b 4d5c03c d44c8f6 4d5c03c d44c8f6 565c0c9 4d5c03c 565c0c9 4d5c03c d44c8f6 4d5c03c 57afd7b 4d5c03c 565c0c9 4d5c03c 565c0c9 4d5c03c 565c0c9 c19f0dd 565c0c9 4d5c03c c19f0dd 4d5c03c c19f0dd 4d5c03c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 | {
"_name_or_path": "/scratch/elec/puhe/p/palp3/sami_ASR/downloaded-base-sami/wav2vec2-base-sami-22k-finetuned",
"activation_dropout": 0.0,
"adapter_attn_dim": null,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 256,
"contrastive_logits_temperature": 0.1,
"conv_bias": false,
"conv_dim": [
512,
512,
512,
512,
512,
512,
512
],
"conv_kernel": [
10,
3,
3,
3,
3,
2,
2
],
"conv_stride": [
5,
2,
2,
2,
2,
2,
2
],
"ctc_loss_reduction": "mean",
"ctc_zero_infinity": false,
"diversity_loss_weight": 0.1,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_norm": "group",
"feat_proj_dropout": 0.0,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_adapter_layers": 3,
"num_attention_heads": 12,
"num_codevector_groups": 2,
"num_codevectors_per_group": 320,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"num_negatives": 100,
"output_hidden_size": 768,
"pad_token_id": 0,
"proj_codevector_dim": 256,
"tdnn_dilation": [
1,
2,
3,
1,
1
],
"tdnn_dim": [
512,
512,
512,
512,
1500
],
"tdnn_kernel": [
5,
3,
3,
1,
1
],
"torch_dtype": "float32",
"transformers_version": "4.48.3",
"use_weighted_layer_sum": false,
"vocab_size": 46,
"xvector_output_dim": 512
}
|