Duplicate from goooofy/zerovox-g2p-autoreg-zamia-de

Co-authored-by: Günter Bartsch <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,9 @@
+German DeepPhonemizer autoregressive transformer based g2p model, intended to be used in zerovox
+
+https://github.com/gooofy/zerovox
+
+based on the Zamia Speech phoneset.
+
+---
+license: apache-2.0
+---

best.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d3fe3104df06f12a473018be3c037e8eee4fe60e81b9b46cde1c4447f66791
+size 275459932

config.yaml

@@ -0,0 +1,14 @@
+preprocessing:
+
+  graphemes: 'abcdefghijklmnopqrstuvwxyzäöüß0123456789-''áãåçèéêëíñóôøúûāćđğıőśşżžșțọứàʿîùăėęłšâïðòý'
+  phonemes: ["'a", "'aɪ", "'aʊ", "'aː", "'e", "'eː", "'i", "'iː", "'o", "'oː", "'u", "'uː", "'y", "'yː", "'æ", "'ø", "'øː", "'œ", "'ɐ", "'ɑ", "'ɑː", "'ɔ", "'ɔɪ", "'ɔʏ", "'ɔː", "'ə", "'ɛ", "'ɛː", "'ɜ", "'ɜː", "'ɪ", "'ʊ", "'ʌ", "'ʏ", "'ʔa", "'ʔaɪ", "'ʔaʊ", "'ʔaː", "'ʔe", "'ʔeː", "'ʔi", "'ʔiː", "'ʔo", "'ʔoː", "'ʔu", "'ʔuː", "'ʔy", "'ʔyː", "'ʔæ", "'ʔø", "'ʔøː", "'ʔœ", "'ʔɑ", "'ʔɑː", "'ʔɔ", "'ʔɔɪ", "'ʔɔʏ", "'ʔə", "'ʔɛ", "'ʔɛː", "'ʔɪ", "'ʔʊ", "'ʔʌ", "'ʔʏ", 'a', 'aɪ', 'aʊ', 'aː', 'b', 'd', 'e', 'eː', 'f', 'g', 'h', 'i', 'iː', 'j', 'k', 'l', 'm', 'n', 'o', 'oː', 'p', 'r', 's', 't', 'u', 'uː', 'v', 'w', 'x', 'y', 'yː', 'z', 'æ', 'ç', 'ð', 'ø', 'øː', 'œ', 'ɐ', 'ɑ', 'ɑː', 'ɔ', 'ɔɪ', 'ɔʏ', 'ɔː', 'ə', 'ɛ', 'ɛː', 'ɜ', 'ɜː', 'ɥ', 'ɪ', 'ɳ', 'ʁ', 'ʃ', 'ʊ', 'ʌ', 'ʏ', 'ʒ', 'ʔa', 'ʔaɪ', 'ʔaʊ', 'ʔaː', 'ʔe', 'ʔeː', 'ʔi', 'ʔiː', 'ʔo', 'ʔoː', 'ʔu', 'ʔuː', 'ʔy', 'ʔyː', 'ʔæ', 'ʔøː', 'ʔɐ', 'ʔɔ', 'ʔɔɪ', 'ʔɔʏ', 'ʔɔː', 'ʔə', 'ʔɛ', 'ʔɛː', 'ʔɪ', 'ʔʊ', 'ʔʏ', 'θ']
+
+model:
+
+  type: 'autoreg_transformer'        # Whether to use a forward transformer or autoregressive transformer model.
+                                     # Choices: ['transformer', 'autoreg_transformer']
+  d_model: 512
+  d_fft: 1024
+  layers: 4
+  dropout: 0.1
+  heads: 4