Skip to content

GitLab

Commit 2a5fe5ff authored by Zhaoheng Ni's avatar Zhaoheng Ni Committed by Facebook GitHub Bot
Browse files

Remove facebook folder in wav2vec unittests (#2015) 

Summary:
Pull Request resolved: https://github.com/pytorch/audio/pull/2015

as titled

Reviewed By: hwangjeff, mthrok

Differential Revision: D32495691

fbshipit-source-id: 60d8a2337585e3147f24ca9f0b6518e30cd9134a
parent 8af01f0a
Show whitespace changes
Inline Side-by-side
Showing with 706 additions and 10 deletions
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-base-10k-voxpopuli.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2Model"
],
"attention_dropout": 0.1,
"bos_token_id": 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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "group",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-base-960h.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "group",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-base.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.0,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2Model"
],
"attention_dropout": 0.1,
"bos_token_id": 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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_norm": "group",
"feat_proj_dropout": 0.1,
"final_dropout": 0.0,
"freeze_feat_extract_train": true,
"gradient_checkpointing": true,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"layerdrop": 0.05,
"mask_channel_length": 10,
"mask_channel_min_space": 1,
"mask_channel_other": 0.0,
"mask_channel_prob": 0.0,
"mask_channel_selection": "static",
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_space": 1,
"mask_time_other": 0.0,
"mask_time_prob": 0.05,
"mask_time_selection": "static",
"model_type": "wav2vec2",
"no_mask_channel_overlap": false,
"no_mask_time_overlap": false,
"num_attention_heads": 12,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-960h-lv60-self.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"conv_bias": true,
"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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-960h-lv60.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"conv_bias": true,
"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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-960h.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "group",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-lv60.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2Model"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"conv_bias": true,
"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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-xlsr-53-german.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForCTC"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"conv_bias": true,
"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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 36
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large-xlsr-53.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.0,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2Model"
],
"attention_dropout": 0.1,
"bos_token_id": 1,
"conv_bias": true,
"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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"final_dropout": 0.0,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_channel_length": 10,
"mask_channel_min_space": 1,
"mask_channel_other": 0.0,
"mask_channel_prob": 0.0,
"mask_channel_selection": "static",
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_space": 1,
"mask_time_other": 0.0,
"mask_time_prob": 0.075,
"mask_time_selection": "static",
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/assets/wav2vec2/huggingface/wav2vec2-large.json 0 → 100644
View file @ 2a5fe5ff
{
"activation_dropout": 0.1,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2Model"
],
"attention_dropout": 0.1,
"bos_token_id": 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": "sum",
"ctc_zero_infinity": false,
"do_stable_layer_norm": false,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "group",
"feat_proj_dropout": 0.1,
"final_dropout": 0.1,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"mask_feature_length": 10,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_attention_heads": 16,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"pad_token_id": 0,
"transformers_version": "4.5.1",
"vocab_size": 32
}
test/torchaudio_unittest/models/wav2vec2/huggingface_intergration_test.py
View file @ 2a5fe5ff
......@@ -26,17 +26,17 @@ def _name_func(testcase_func, i, param):
# Pretrained
HF_BASE = _load_config('facebook', 'wav2vec2-base')
HF_LARGE = _load_config('facebook', 'wav2vec2-large')
HF_LARGE_LV60 = _load_config('facebook', 'wav2vec2-large-lv60')
HF_LARGE_XLSR_53 = _load_config('facebook', 'wav2vec2-large-xlsr-53')
HF_BASE_10K_VOXPOPULI = _load_config('facebook', 'wav2vec2-base-10k-voxpopuli')
HF_BASE = _load_config('wav2vec2-base')
HF_LARGE = _load_config('wav2vec2-large')
HF_LARGE_LV60 = _load_config('wav2vec2-large-lv60')
HF_LARGE_XLSR_53 = _load_config('wav2vec2-large-xlsr-53')
HF_BASE_10K_VOXPOPULI = _load_config('wav2vec2-base-10k-voxpopuli')
# Finetuned
HF_BASE_960H = _load_config('facebook', 'wav2vec2-base-960h')
HF_LARGE_960H = _load_config('facebook', 'wav2vec2-large-960h')
HF_LARGE_LV60_960H = _load_config('facebook', 'wav2vec2-large-960h-lv60')
HF_LARGE_LV60_SELF_960H = _load_config('facebook', 'wav2vec2-large-960h-lv60-self')
HF_LARGE_XLSR_DE = _load_config('facebook', 'wav2vec2-large-xlsr-53-german')
HF_BASE_960H = _load_config('wav2vec2-base-960h')
HF_LARGE_960H = _load_config('wav2vec2-large-960h')
HF_LARGE_LV60_960H = _load_config('wav2vec2-large-960h-lv60')
HF_LARGE_LV60_SELF_960H = _load_config('wav2vec2-large-960h-lv60-self')
HF_LARGE_XLSR_DE = _load_config('wav2vec2-large-xlsr-53-german')
# Config and corresponding factory functions
PRETRAIN_CONFIGS = parameterized.expand([
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment