sep moods

README.md

@@ -1,3 +1,13 @@
 ---
-license: gpl-3.0
+library_name: fairseq
+task: text-to-speech
+tags:
+- fairseq
+- audio
+- text-to-speech
+language: en
+widget:
+- text: "Hello, this is a test run."
+  example_title: "Hello, this is a test run."
 ---
+# fastspeech2-mf4

config.yaml

@@ -0,0 +1,33 @@
+audio_root: ./
+features:
+  energy_max: 5.850490093231201
+  energy_min: 0.0
+  eps: 1.0e-05
+  f_max: 8000
+  f_min: 0
+  hop_len_t: 0.011609977324263039
+  hop_length: 256
+  n_fft: 1024
+  n_mels: 80
+  n_stft: 513
+  pitch_max: 6.524898211542482
+  pitch_min: 1.0e-08
+  sample_rate: 22050
+  type: spectrogram+melscale+log
+  win_len_t: 0.046439909297052155
+  win_length: 1024
+  window_fn: hann
+global_cmvn:
+  stats_npz_path: gcmvn_stats.npz
+sample_rate: 22050
+transforms:
+  '*':
+  - global_cmvn
+vocab_filename: vocab.txt
+speaker_set_filename: speakers.txt
+vocoder:
+  type: hifigan
+  config: hifigan.json
+  checkpoint: hifigan.bin
+hub:
+  phonemizer: g2p

hifigan.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc43f2a7cff67b91696c67cb577391be2ed64cd9bc10aedcc9e08bb7c0b03e44
+size 55819885

hifigan.json

@@ -0,0 +1,37 @@
+{
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 16,
+    "learning_rate": 0.0002,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.999,
+    "seed": 1234,
+
+    "upsample_rates": [8,8,2,2],
+    "upsample_kernel_sizes": [16,16,4,4],
+    "upsample_initial_channel": 512,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+
+    "segment_size": 8192,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 256,
+    "win_size": 1024,
+
+    "sampling_rate": 22050,
+
+    "fmin": 0,
+    "fmax": 8000,
+    "fmax_for_loss": null,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea0fd38660ca493154d720cbf2a111b5a7ba135e59da4c4f5d44841333b604a
+size 387441213

speakers.txt

@@ -0,0 +1,4 @@
+Freeman angry
+Freeman happy
+Freeman narration
+Freeman normal

vocab.txt

@@ -0,0 +1,70 @@
+N 333705
+T 328991
+AH0 293550
+S 266464
+R 228299
+L 206080
+D 205594
+IH0 182689
+K 164159
+sp 142640
+M 138027
+Z 122502
+IH1 116897
+AA1 113508
+TH 113159
+F 112260
+EH1 104541
+P 101009
+W 93292
+ER0 89396
+B 87421
+IY0 83572
+AE1 80417
+HH 77016
+EY1 76588
+AO1 75558
+AY1 70751
+AH1 63903
+V 58163
+UW1 54663
+IY1 51596
+NG 49090
+OW0 47402
+G 44006
+Y 41567
+SH 41278
+DH 40317
+OW1 37952
+AE2 36196
+ER1 30813
+JH 29213
+CH 24021
+AW1 20297
+UH1 18645
+EH2 12445
+EY2 10405
+IH2 8282
+OW2 7128
+AY2 7050
+UW0 6859
+AA2 5578
+OY1 5382
+AA0 5067
+AO2 4570
+AW2 4526
+AO0 3906
+EH0 3684
+AE0 3635
+IY2 3150
+ZH 3126
+UW2 3107
+AY0 2345
+AH2 2238
+UH2 1020
+ER2 973
+EY0 816
+AW0 558
+UH0 295
+OY2 266
+OY0 84