Upload 26 files
Browse files- feature_extractor/preprocessor_config.json +22 -0
- language_model/config.json +39 -0
- language_model/pytorch_model.bin +3 -0
- model_index.json +48 -0
- projection_model/config.json +9 -0
- projection_model/diffusion_pytorch_model.bin +3 -0
- scheduler/scheduler_config.json +19 -0
- text_encoder/config.json +35 -0
- text_encoder/pytorch_model.bin +3 -0
- text_encoder_2/config.json +82 -0
- text_encoder_2/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +51 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +62 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/added_tokens.json +3 -0
- tokenizer_2/special_tokens_map.json +4 -0
- tokenizer_2/tokenizer_config.json +30 -0
- tokenizer_2/vocab.json +40 -0
- unet/config.json +70 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +28 -0
- vae/diffusion_pytorch_model.bin +3 -0
- vocoder/config.json +50 -0
- vocoder/pytorch_model.bin +3 -0
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length_s": 10,
|
3 |
+
"feature_extractor_type": "ClapFeatureExtractor",
|
4 |
+
"feature_size": 64,
|
5 |
+
"fft_window_size": 1024,
|
6 |
+
"frequency_max": 14000,
|
7 |
+
"frequency_min": 50,
|
8 |
+
"hop_length": 480,
|
9 |
+
"max_length_s": 10,
|
10 |
+
"n_fft": 1024,
|
11 |
+
"nb_frequency_bins": 513,
|
12 |
+
"nb_max_frames": 1000,
|
13 |
+
"nb_max_samples": 480000,
|
14 |
+
"padding": "repeatpad",
|
15 |
+
"padding_side": "right",
|
16 |
+
"padding_value": 0.0,
|
17 |
+
"processor_class": "ClapProcessor",
|
18 |
+
"return_attention_mask": false,
|
19 |
+
"sampling_rate": 48000,
|
20 |
+
"top_db": null,
|
21 |
+
"truncation": "rand_trunc"
|
22 |
+
}
|
language_model/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2Model"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"max_new_tokens": 8,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.40.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
language_model/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61b9875d359ede0388ec159ff3e446a69406cc8e01160de4fb0afcb654bb8359
|
3 |
+
size 497803738
|
model_index.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AudioLDM2Pipeline",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"ClapFeatureExtractor"
|
7 |
+
],
|
8 |
+
"language_model": [
|
9 |
+
"transformers",
|
10 |
+
"GPT2Model"
|
11 |
+
],
|
12 |
+
"projection_model": [
|
13 |
+
"audioldm2",
|
14 |
+
"AudioLDM2ProjectionModel"
|
15 |
+
],
|
16 |
+
"scheduler": [
|
17 |
+
"diffusers",
|
18 |
+
"DDIMScheduler"
|
19 |
+
],
|
20 |
+
"text_encoder": [
|
21 |
+
"transformers",
|
22 |
+
"ClapModel"
|
23 |
+
],
|
24 |
+
"text_encoder_2": [
|
25 |
+
"transformers",
|
26 |
+
"VitsModel"
|
27 |
+
],
|
28 |
+
"tokenizer": [
|
29 |
+
"transformers",
|
30 |
+
"RobertaTokenizerFast"
|
31 |
+
],
|
32 |
+
"tokenizer_2": [
|
33 |
+
"transformers",
|
34 |
+
"VitsTokenizer"
|
35 |
+
],
|
36 |
+
"unet": [
|
37 |
+
"audioldm2",
|
38 |
+
"AudioLDM2UNet2DConditionModel"
|
39 |
+
],
|
40 |
+
"vae": [
|
41 |
+
"diffusers",
|
42 |
+
"AutoencoderKL"
|
43 |
+
],
|
44 |
+
"vocoder": [
|
45 |
+
"transformers",
|
46 |
+
"SpeechT5HifiGan"
|
47 |
+
]
|
48 |
+
}
|
projection_model/config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AudioLDM2ProjectionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"langauge_model_dim": 768,
|
5 |
+
"max_seq_length": 310,
|
6 |
+
"text_encoder_1_dim": 192,
|
7 |
+
"text_encoder_dim": 512,
|
8 |
+
"use_learned_position_embedding": true
|
9 |
+
}
|
projection_model/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2643753807ae5cf4d312b5098b484f0e0371159d568bb7803d35c10ed2b5ec1
|
3 |
+
size 2184512
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"beta_end": 0.0195,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.0015,
|
7 |
+
"clip_sample": false,
|
8 |
+
"clip_sample_range": 1.0,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "epsilon",
|
12 |
+
"rescale_betas_zero_snr": false,
|
13 |
+
"sample_max_value": 1.0,
|
14 |
+
"set_alpha_to_one": false,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"thresholding": false,
|
17 |
+
"timestep_spacing": "leading",
|
18 |
+
"trained_betas": null
|
19 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ClapModel"
|
4 |
+
],
|
5 |
+
"audio_config": {
|
6 |
+
"depths": [
|
7 |
+
2,
|
8 |
+
2,
|
9 |
+
12,
|
10 |
+
2
|
11 |
+
],
|
12 |
+
"fusion_num_hidden_layers": 2,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"model_type": "clap_audio_model",
|
15 |
+
"patch_embeds_hidden_size": 128,
|
16 |
+
"projection_hidden_size": 768
|
17 |
+
},
|
18 |
+
"hidden_size": 768,
|
19 |
+
"initializer_factor": 1.0,
|
20 |
+
"logit_scale_init_value": 14.285714285714285,
|
21 |
+
"model_type": "clap",
|
22 |
+
"num_hidden_layers": 16,
|
23 |
+
"projection_dim": 512,
|
24 |
+
"projection_hidden_act": "relu",
|
25 |
+
"text_config": {
|
26 |
+
"classifier_dropout": null,
|
27 |
+
"fusion_hidden_size": 768,
|
28 |
+
"fusion_num_hidden_layers": 2,
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"model_type": "clap_text_model",
|
31 |
+
"projection_hidden_size": 768
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.40.0"
|
35 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5273abc4ce184eac0e026002b27b1e197037e2a107184a71f6ebb5afb4090d6a
|
3 |
+
size 776445110
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"architectures": [
|
4 |
+
"VitsModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"depth_separable_channels": 2,
|
8 |
+
"depth_separable_num_layers": 3,
|
9 |
+
"duration_predictor_dropout": 0.5,
|
10 |
+
"duration_predictor_filter_channels": 256,
|
11 |
+
"duration_predictor_flow_bins": 10,
|
12 |
+
"duration_predictor_kernel_size": 3,
|
13 |
+
"duration_predictor_num_flows": 4,
|
14 |
+
"duration_predictor_tail_bound": 5.0,
|
15 |
+
"ffn_dim": 768,
|
16 |
+
"ffn_kernel_size": 3,
|
17 |
+
"flow_size": 192,
|
18 |
+
"hidden_act": "relu",
|
19 |
+
"hidden_dropout": 0.1,
|
20 |
+
"hidden_size": 192,
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"layer_norm_eps": 1e-05,
|
23 |
+
"layerdrop": 0.1,
|
24 |
+
"leaky_relu_slope": 0.1,
|
25 |
+
"model_type": "vits",
|
26 |
+
"noise_scale": 0.667,
|
27 |
+
"noise_scale_duration": 0.8,
|
28 |
+
"num_attention_heads": 2,
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"num_speakers": 1,
|
31 |
+
"posterior_encoder_num_wavenet_layers": 16,
|
32 |
+
"prior_encoder_num_flows": 4,
|
33 |
+
"prior_encoder_num_wavenet_layers": 4,
|
34 |
+
"resblock_dilation_sizes": [
|
35 |
+
[
|
36 |
+
1,
|
37 |
+
3,
|
38 |
+
5
|
39 |
+
],
|
40 |
+
[
|
41 |
+
1,
|
42 |
+
3,
|
43 |
+
5
|
44 |
+
],
|
45 |
+
[
|
46 |
+
1,
|
47 |
+
3,
|
48 |
+
5
|
49 |
+
]
|
50 |
+
],
|
51 |
+
"resblock_kernel_sizes": [
|
52 |
+
3,
|
53 |
+
7,
|
54 |
+
11
|
55 |
+
],
|
56 |
+
"sampling_rate": 16000,
|
57 |
+
"speaker_embedding_size": 0,
|
58 |
+
"speaking_rate": 1.0,
|
59 |
+
"spectrogram_bins": 513,
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.40.0",
|
62 |
+
"upsample_initial_channel": 512,
|
63 |
+
"upsample_kernel_sizes": [
|
64 |
+
16,
|
65 |
+
16,
|
66 |
+
4,
|
67 |
+
4
|
68 |
+
],
|
69 |
+
"upsample_rates": [
|
70 |
+
8,
|
71 |
+
8,
|
72 |
+
2,
|
73 |
+
2
|
74 |
+
],
|
75 |
+
"use_bias": true,
|
76 |
+
"use_stochastic_duration_prediction": true,
|
77 |
+
"vocab_size": 183,
|
78 |
+
"wavenet_dilation_rate": 1,
|
79 |
+
"wavenet_dropout": 0.0,
|
80 |
+
"wavenet_kernel_size": 5,
|
81 |
+
"window_size": 4
|
82 |
+
}
|
text_encoder_2/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe24d9d769139201e6fe80d0fc42574bd4e2ad9d58ded5d2cdc777bf1e467ae6
|
3 |
+
size 145503282
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": null,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"processor_class": "ClapProcessor",
|
58 |
+
"sep_token": "</s>",
|
59 |
+
"tokenizer_class": "RobertaTokenizer",
|
60 |
+
"trim_offsets": true,
|
61 |
+
"unk_token": "<unk>"
|
62 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 38
|
3 |
+
}
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "k",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_blank": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "k",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"38": {
|
13 |
+
"content": "<unk>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"clean_up_tokenization_spaces": true,
|
22 |
+
"is_uroman": false,
|
23 |
+
"language": "eng",
|
24 |
+
"model_max_length": 1000000000000000019884624838656,
|
25 |
+
"normalize": true,
|
26 |
+
"pad_token": "k",
|
27 |
+
"phonemize": false,
|
28 |
+
"tokenizer_class": "VitsTokenizer",
|
29 |
+
"unk_token": "<unk>"
|
30 |
+
}
|
tokenizer_2/vocab.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 19,
|
3 |
+
"'": 1,
|
4 |
+
"-": 14,
|
5 |
+
"0": 23,
|
6 |
+
"1": 15,
|
7 |
+
"2": 28,
|
8 |
+
"3": 11,
|
9 |
+
"4": 27,
|
10 |
+
"5": 35,
|
11 |
+
"6": 36,
|
12 |
+
"_": 30,
|
13 |
+
"a": 26,
|
14 |
+
"b": 24,
|
15 |
+
"c": 12,
|
16 |
+
"d": 5,
|
17 |
+
"e": 7,
|
18 |
+
"f": 20,
|
19 |
+
"g": 37,
|
20 |
+
"h": 6,
|
21 |
+
"i": 18,
|
22 |
+
"j": 16,
|
23 |
+
"k": 0,
|
24 |
+
"l": 21,
|
25 |
+
"m": 17,
|
26 |
+
"n": 29,
|
27 |
+
"o": 22,
|
28 |
+
"p": 13,
|
29 |
+
"q": 34,
|
30 |
+
"r": 25,
|
31 |
+
"s": 8,
|
32 |
+
"t": 33,
|
33 |
+
"u": 4,
|
34 |
+
"v": 32,
|
35 |
+
"w": 9,
|
36 |
+
"x": 31,
|
37 |
+
"y": 3,
|
38 |
+
"z": 2,
|
39 |
+
"–": 10
|
40 |
+
}
|
unet/config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AudioLDM2UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": 8,
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
384,
|
10 |
+
640
|
11 |
+
],
|
12 |
+
"class_embed_type": null,
|
13 |
+
"class_embeddings_concat": false,
|
14 |
+
"conv_in_kernel": 3,
|
15 |
+
"conv_out_kernel": 3,
|
16 |
+
"cross_attention_dim": [
|
17 |
+
[
|
18 |
+
null,
|
19 |
+
768
|
20 |
+
],
|
21 |
+
[
|
22 |
+
null,
|
23 |
+
768
|
24 |
+
],
|
25 |
+
[
|
26 |
+
null,
|
27 |
+
768
|
28 |
+
],
|
29 |
+
[
|
30 |
+
null,
|
31 |
+
768
|
32 |
+
]
|
33 |
+
],
|
34 |
+
"down_block_types": [
|
35 |
+
"DownBlock2D",
|
36 |
+
"CrossAttnDownBlock2D",
|
37 |
+
"CrossAttnDownBlock2D",
|
38 |
+
"CrossAttnDownBlock2D"
|
39 |
+
],
|
40 |
+
"downsample_padding": 1,
|
41 |
+
"flip_sin_to_cos": true,
|
42 |
+
"freq_shift": 0,
|
43 |
+
"in_channels": 8,
|
44 |
+
"layers_per_block": 2,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"out_channels": 8,
|
53 |
+
"projection_class_embeddings_input_dim": null,
|
54 |
+
"resnet_time_scale_shift": "default",
|
55 |
+
"sample_size": 262,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": 1,
|
62 |
+
"up_block_types": [
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D",
|
65 |
+
"CrossAttnUpBlock2D",
|
66 |
+
"UpBlock2D"
|
67 |
+
],
|
68 |
+
"upcast_attention": false,
|
69 |
+
"use_linear_projection": false
|
70 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b4581dff5be823ae01371ce6bc4a69f79d5750e93a0d6e3bf85e86c282ccdc
|
3 |
+
size 1048171066
|
vae/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"block_out_channels": [
|
6 |
+
128,
|
7 |
+
256,
|
8 |
+
512
|
9 |
+
],
|
10 |
+
"down_block_types": [
|
11 |
+
"DownEncoderBlock2D",
|
12 |
+
"DownEncoderBlock2D",
|
13 |
+
"DownEncoderBlock2D"
|
14 |
+
],
|
15 |
+
"force_upcast": true,
|
16 |
+
"in_channels": 1,
|
17 |
+
"latent_channels": 8,
|
18 |
+
"layers_per_block": 2,
|
19 |
+
"norm_num_groups": 32,
|
20 |
+
"out_channels": 1,
|
21 |
+
"sample_size": 1048,
|
22 |
+
"scaling_factor": 0.41837412118911743,
|
23 |
+
"up_block_types": [
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D"
|
27 |
+
]
|
28 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c4201e7ebec40dc21ed45d99077db20fd5020dbe5886269e3b83108cd2c4e16
|
3 |
+
size 221587226
|
vocoder/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SpeechT5HifiGan"
|
4 |
+
],
|
5 |
+
"initializer_range": 0.01,
|
6 |
+
"leaky_relu_slope": 0.1,
|
7 |
+
"model_in_dim": 64,
|
8 |
+
"model_type": "hifigan",
|
9 |
+
"normalize_before": false,
|
10 |
+
"resblock_dilation_sizes": [
|
11 |
+
[
|
12 |
+
1,
|
13 |
+
3,
|
14 |
+
5
|
15 |
+
],
|
16 |
+
[
|
17 |
+
1,
|
18 |
+
3,
|
19 |
+
5
|
20 |
+
],
|
21 |
+
[
|
22 |
+
1,
|
23 |
+
3,
|
24 |
+
5
|
25 |
+
]
|
26 |
+
],
|
27 |
+
"resblock_kernel_sizes": [
|
28 |
+
3,
|
29 |
+
7,
|
30 |
+
11
|
31 |
+
],
|
32 |
+
"sampling_rate": 16000,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.40.0",
|
35 |
+
"upsample_initial_channel": 1024,
|
36 |
+
"upsample_kernel_sizes": [
|
37 |
+
16,
|
38 |
+
16,
|
39 |
+
8,
|
40 |
+
4,
|
41 |
+
4
|
42 |
+
],
|
43 |
+
"upsample_rates": [
|
44 |
+
5,
|
45 |
+
4,
|
46 |
+
2,
|
47 |
+
2,
|
48 |
+
2
|
49 |
+
]
|
50 |
+
}
|
vocoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bfa544480458b5175cb0664a2bc1cc615c2b83c19c71d2c8c3002bba3c93bde
|
3 |
+
size 221120794
|