Commit
·
c44455c
1
Parent(s):
063a2f0
Upload model
Browse files- config.json +63 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"acoustic_dim": 384,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"FastSpeech2ConformerModel"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"decoder_attention_dropout_rate": 0.2,
|
| 8 |
+
"decoder_concat_after": false,
|
| 9 |
+
"decoder_dropout_rate": 0.2,
|
| 10 |
+
"decoder_kernel_size": 31,
|
| 11 |
+
"decoder_layers": 4,
|
| 12 |
+
"decoder_linear_units": 1536,
|
| 13 |
+
"decoder_normalize_before": false,
|
| 14 |
+
"decoder_positional_dropout_rate": 0.2,
|
| 15 |
+
"duration_predictor_channels": 256,
|
| 16 |
+
"duration_predictor_dropout_rate": 0.2,
|
| 17 |
+
"duration_predictor_kernel_size": 3,
|
| 18 |
+
"duration_predictor_layers": 2,
|
| 19 |
+
"encoder_attention_dropout_rate": 0.2,
|
| 20 |
+
"encoder_concat_after": false,
|
| 21 |
+
"encoder_dropout_rate": 0.2,
|
| 22 |
+
"encoder_kernel_size": 7,
|
| 23 |
+
"encoder_layers": 4,
|
| 24 |
+
"encoder_linear_units": 1536,
|
| 25 |
+
"encoder_normalize_before": false,
|
| 26 |
+
"encoder_positional_dropout_rate": 0.2,
|
| 27 |
+
"energy_embed_dropout": 0.0,
|
| 28 |
+
"energy_embed_kernel_size": 1,
|
| 29 |
+
"energy_predictor_channels": 256,
|
| 30 |
+
"energy_predictor_dropout": 0.5,
|
| 31 |
+
"energy_predictor_kernel_size": 3,
|
| 32 |
+
"energy_predictor_layers": 2,
|
| 33 |
+
"eos_token_id": 2,
|
| 34 |
+
"input_dim": 78,
|
| 35 |
+
"lang_embs": null,
|
| 36 |
+
"model_type": "fastspeech2_conformer",
|
| 37 |
+
"num_attention_heads": 2,
|
| 38 |
+
"output_dim": 80,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"pitch_embed_dropout": 0.0,
|
| 41 |
+
"pitch_embed_kernel_size": 1,
|
| 42 |
+
"pitch_predictor_channels": 256,
|
| 43 |
+
"pitch_predictor_dropout": 0.5,
|
| 44 |
+
"pitch_predictor_kernel_size": 5,
|
| 45 |
+
"pitch_predictor_layers": 5,
|
| 46 |
+
"positionwise_conv_kernel_size": 3,
|
| 47 |
+
"postnet_channels": 256,
|
| 48 |
+
"postnet_dropout_rate": 0.5,
|
| 49 |
+
"postnet_filters": 5,
|
| 50 |
+
"postnet_layers": 5,
|
| 51 |
+
"reduction_factor": 1,
|
| 52 |
+
"stop_gradient_from_energy_predictor": false,
|
| 53 |
+
"stop_gradient_from_pitch_predictor": true,
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.30.0.dev0",
|
| 56 |
+
"use_batch_norm": true,
|
| 57 |
+
"use_cnn_in_conformer": true,
|
| 58 |
+
"use_macaron_style_in_conformer": true,
|
| 59 |
+
"use_masking": true,
|
| 60 |
+
"use_weighted_masking": false,
|
| 61 |
+
"utt_embed_dim": null,
|
| 62 |
+
"vocab_size": 75
|
| 63 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edff08e1cbec2744f4d0d6edb8ee380cd54dc4b09a123a6cd39691bad49deda4
|
| 3 |
+
size 281200269
|