gyt1145028706
commited on
Commit
·
c834337
1
Parent(s):
6171706
add
Browse files- config.json +0 -120
- examples/m1.wav +0 -0
- preprocessor_config.json +0 -13
- pytorch_model.bin +0 -3
config.json
DELETED
|
@@ -1,120 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"model_type": "xy_tokenizer",
|
| 3 |
-
"input_sample_rate": 16000,
|
| 4 |
-
"output_sample_rate": 24000,
|
| 5 |
-
"encoder_downsample_rate": 1280,
|
| 6 |
-
"decoder_upsample_rate": 1920,
|
| 7 |
-
"code_dim": 3072,
|
| 8 |
-
"params": {
|
| 9 |
-
"feature_extractor_kwargs": {
|
| 10 |
-
"chunk_length": 30,
|
| 11 |
-
"feature_size": 80,
|
| 12 |
-
"hop_length": 160,
|
| 13 |
-
"n_fft": 400,
|
| 14 |
-
"n_samples": 480000,
|
| 15 |
-
"nb_max_frames": 3000,
|
| 16 |
-
"padding_side": "right",
|
| 17 |
-
"padding_value": 0.0,
|
| 18 |
-
"sampling_rate": 16000,
|
| 19 |
-
"return_attention_mask": true,
|
| 20 |
-
"return_tensors": "pt"
|
| 21 |
-
},
|
| 22 |
-
"semantic_encoder_kwargs": {
|
| 23 |
-
"num_mel_bins": 80,
|
| 24 |
-
"sampling_rate": 16000,
|
| 25 |
-
"hop_length": 160,
|
| 26 |
-
"stride_size": 2,
|
| 27 |
-
"kernel_size": 3,
|
| 28 |
-
"d_model": 768,
|
| 29 |
-
"scale_embedding": false,
|
| 30 |
-
"max_audio_seconds": 30,
|
| 31 |
-
"encoder_layers": 12,
|
| 32 |
-
"encoder_attention_heads": 12,
|
| 33 |
-
"encoder_ffn_dim": 3072,
|
| 34 |
-
"activation_function": "gelu"
|
| 35 |
-
},
|
| 36 |
-
"semantic_encoder_adapter_kwargs": {
|
| 37 |
-
"input_dim": 768,
|
| 38 |
-
"output_dim": 768,
|
| 39 |
-
"d_model": 768,
|
| 40 |
-
"max_source_positions": 1500,
|
| 41 |
-
"encoder_layers": 4,
|
| 42 |
-
"encoder_attention_heads": 12,
|
| 43 |
-
"encoder_ffn_dim": 3072
|
| 44 |
-
},
|
| 45 |
-
"acoustic_encoder_kwargs": {
|
| 46 |
-
"num_mel_bins": 80,
|
| 47 |
-
"sampling_rate": 16000,
|
| 48 |
-
"hop_length": 160,
|
| 49 |
-
"stride_size": 2,
|
| 50 |
-
"kernel_size": 3,
|
| 51 |
-
"d_model": 768,
|
| 52 |
-
"scale_embedding": false,
|
| 53 |
-
"max_audio_seconds": 30,
|
| 54 |
-
"encoder_layers": 12,
|
| 55 |
-
"encoder_attention_heads": 12,
|
| 56 |
-
"encoder_ffn_dim": 3072,
|
| 57 |
-
"activation_function": "gelu"
|
| 58 |
-
},
|
| 59 |
-
"pre_rvq_adapter_kwargs": {
|
| 60 |
-
"input_dim": 1536,
|
| 61 |
-
"output_dim": 768,
|
| 62 |
-
"d_model": 768,
|
| 63 |
-
"max_source_positions": 1500,
|
| 64 |
-
"encoder_layers": 4,
|
| 65 |
-
"encoder_attention_heads": 12,
|
| 66 |
-
"encoder_ffn_dim": 3072
|
| 67 |
-
},
|
| 68 |
-
"downsample_kwargs": {
|
| 69 |
-
"d_model": 768,
|
| 70 |
-
"avg_pooler": 4
|
| 71 |
-
},
|
| 72 |
-
"quantizer_kwargs": {
|
| 73 |
-
"input_dim": 3072,
|
| 74 |
-
"rvq_dim": 512,
|
| 75 |
-
"output_dim": 3072,
|
| 76 |
-
"num_quantizers": 8,
|
| 77 |
-
"codebook_size": 1024,
|
| 78 |
-
"codebook_dim": 512,
|
| 79 |
-
"quantizer_dropout": 0.0
|
| 80 |
-
},
|
| 81 |
-
"post_rvq_adapter_kwargs": {
|
| 82 |
-
"input_dim": 3072,
|
| 83 |
-
"output_dim": 3072,
|
| 84 |
-
"d_model": 768,
|
| 85 |
-
"max_source_positions": 375,
|
| 86 |
-
"encoder_layers": 4,
|
| 87 |
-
"encoder_attention_heads": 12,
|
| 88 |
-
"encoder_ffn_dim": 3072
|
| 89 |
-
},
|
| 90 |
-
"upsample_kwargs": {
|
| 91 |
-
"d_model": 768,
|
| 92 |
-
"stride": 4
|
| 93 |
-
},
|
| 94 |
-
"acoustic_decoder_kwargs": {
|
| 95 |
-
"num_mel_bins": 80,
|
| 96 |
-
"sampling_rate": 16000,
|
| 97 |
-
"hop_length": 160,
|
| 98 |
-
"stride_size": 2,
|
| 99 |
-
"kernel_size": 3,
|
| 100 |
-
"d_model": 768,
|
| 101 |
-
"scale_embedding": false,
|
| 102 |
-
"max_audio_seconds": 30,
|
| 103 |
-
"decoder_layers": 12,
|
| 104 |
-
"decoder_attention_heads": 12,
|
| 105 |
-
"decoder_ffn_dim": 3072,
|
| 106 |
-
"activation_function": "gelu"
|
| 107 |
-
},
|
| 108 |
-
"vocos_kwargs": {
|
| 109 |
-
"input_channels": 80,
|
| 110 |
-
"dim": 512,
|
| 111 |
-
"intermediate_dim": 4096,
|
| 112 |
-
"num_layers": 30,
|
| 113 |
-
"n_fft": 960,
|
| 114 |
-
"hop_size": 240,
|
| 115 |
-
"padding": "same"
|
| 116 |
-
}
|
| 117 |
-
},
|
| 118 |
-
"torch_dtype": "float32",
|
| 119 |
-
"transformers_version": "4.51.0"
|
| 120 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
examples/m1.wav
DELETED
|
Binary file (64.8 kB)
|
|
|
preprocessor_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chunk_length": 30,
|
| 3 |
-
"feature_size": 80,
|
| 4 |
-
"hop_length": 160,
|
| 5 |
-
"n_fft": 400,
|
| 6 |
-
"n_samples": 480000,
|
| 7 |
-
"nb_max_frames": 3000,
|
| 8 |
-
"padding_side": "right",
|
| 9 |
-
"padding_value": 0.0,
|
| 10 |
-
"sampling_rate": 16000,
|
| 11 |
-
"return_attention_mask": true,
|
| 12 |
-
"return_tensors": "pt"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fafbaf4ba0e6095be842230c4bd16ecf6d193b250718a5775f1ac7aa528d9110
|
| 3 |
-
size 2137279502
|
|
|
|
|
|
|
|
|
|
|
|