[pre-commit.ci] pre-commit autoupdate (#243)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.1.7 → v0.1.8](https://github.com/astral-sh/ruff-pre-commit/compare/v0.1.7...v0.1.8)
- [github.com/psf/black: 23.11.0 → 23.12.0](https://github.com/psf/black/compare/23.11.0...23.12.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

.pre-commit-config.yaml

@@ -7,13 +7,13 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.7
+    rev: v0.1.8
     hooks:
       - id: ruff
         args: [ --fix ]
 
   - repo: https://github.com/psf/black
-    rev: 23.11.0
+    rev: 23.12.0
     hooks:
       - id: black
 

onnx_modules/V220_OnnxInference/__init__.py

@@ -1,17 +1,20 @@
 import numpy as np
 import onnxruntime as ort
 
+
 def convert_pad_shape(pad_shape):
     layer = pad_shape[::-1]
     pad_shape = [item for sublist in layer for item in sublist]
     return pad_shape
 
+
 def sequence_mask(length, max_length=None):
     if max_length is None:
         max_length = length.max()
     x = np.arange(max_length, dtype=length.dtype)
     return np.expand_dims(x, 0) < np.expand_dims(length, 1)
 
+
 def generate_path(duration, mask):
     """
     duration: [b, 1, t_x]
@@ -28,8 +31,9 @@ def generate_path(duration, mask):
     path = np.expand_dims(path, 1).transpose(0, 1, 3, 2)
     return path
 
-class OnnxInferenceSession():
+
-    def __init__(self, path, Providers = ["CPUExecutionProvider"]):
+class OnnxInferenceSession:
+    def __init__(self, path, Providers=["CPUExecutionProvider"]):
         self.enc = ort.InferenceSession(path["enc"], providers=Providers)
         self.emb_g = ort.InferenceSession(path["emb_g"], providers=Providers)
         self.dp = ort.InferenceSession(path["dp"], providers=Providers)
@@ -47,34 +51,47 @@ class OnnxInferenceSession():
         bert_en,
         emo,
         sid,
-            seed = 114514,
+        seed=114514,
-            seq_noise_scale = 0.8,
+        seq_noise_scale=0.8,
-            sdp_noise_scale = 0.6,
+        sdp_noise_scale=0.6,
-            length_scale = 1.,
+        length_scale=1.0,
-            sdp_ratio = 0.
+        sdp_ratio=0.0,
     ):
-        g = self.emb_g.run(None, {'sid': sid.astype(np.int64),})[0]
+        g = self.emb_g.run(
+            None,
+            {
+                "sid": sid.astype(np.int64),
+            },
+        )[0]
         g = np.expand_dims(g, -1)
         enc_rtn = self.enc.run(
             None,
             {
-                "x" : seq.astype(np.int64),
+                "x": seq.astype(np.int64),
-                "t" : tone.astype(np.int64),
+                "t": tone.astype(np.int64),
-                "language" : language.astype(np.int64),
+                "language": language.astype(np.int64),
-                "bert_0" : bert_zh.astype(np.float32),
+                "bert_0": bert_zh.astype(np.float32),
-                "bert_1" : bert_jp.astype(np.float32),
+                "bert_1": bert_jp.astype(np.float32),
-                "bert_2" : bert_en.astype(np.float32),
+                "bert_2": bert_en.astype(np.float32),
-                "emo" : emo.astype(np.float32),
+                "emo": emo.astype(np.float32),
-                "g" : g.astype(np.float32)
+                "g": g.astype(np.float32),
-            })
+            },
+        )
         x, m_p, logs_p, x_mask = enc_rtn[0], enc_rtn[1], enc_rtn[2], enc_rtn[3]
         np.random.seed(seed)
         zinput = np.random.randn(x.shape[0], 2, x.shape[2]) * sdp_noise_scale
-        logw = self.sdp.run(None, {"x" : x, "x_mask" : x_mask, "zin" : zinput.astype(np.float32), "g" : g})[0] * (sdp_ratio) + \
+        logw = self.sdp.run(
-            self.dp.run(None, {"x" : x, "x_mask" : x_mask, "g" : g})[0] * (1 - sdp_ratio)
+            None, {"x": x, "x_mask": x_mask, "zin": zinput.astype(np.float32), "g": g}
+        )[0] * (sdp_ratio) + self.dp.run(None, {"x": x, "x_mask": x_mask, "g": g})[
+            0
+        ] * (
+            1 - sdp_ratio
+        )
         w = np.exp(logw) * x_mask * length_scale
         w_ceil = np.ceil(w)
-        y_lengths = np.clip(np.sum(w_ceil, (1, 2)), a_min=1., a_max=100000).astype(np.int64)
+        y_lengths = np.clip(np.sum(w_ceil, (1, 2)), a_min=1.0, a_max=100000).astype(
+            np.int64
+        )
         y_mask = np.expand_dims(sequence_mask(y_lengths, None), 1)
         attn_mask = np.expand_dims(x_mask, 2) * np.expand_dims(y_mask, -1)
         attn = generate_path(w_ceil, attn_mask)
@@ -85,8 +102,20 @@ class OnnxInferenceSession():
             0, 2, 1
         )  # [b, t', t], [b, t, d] -> [b, d, t']
 
-        z_p = m_p + np.random.randn(m_p.shape[0], m_p.shape[1], m_p.shape[2]) * np.exp(logs_p) * seq_noise_scale
+        z_p = (
+            m_p
+            + np.random.randn(m_p.shape[0], m_p.shape[1], m_p.shape[2])
+            * np.exp(logs_p)
+            * seq_noise_scale
+        )
 
-        z = self.flow.run(None, {"z_p" : z_p.astype(np.float32), "y_mask" : y_mask.astype(np.float32), "g": g})[0]
+        z = self.flow.run(
+            None,
+            {
+                "z_p": z_p.astype(np.float32),
+                "y_mask": y_mask.astype(np.float32),
+                "g": g,
+            },
+        )[0]
 
-        return self.dec.run(None, {"z_in" : z.astype(np.float32), "g": g})[0]
+        return self.dec.run(None, {"z_in": z.astype(np.float32), "g": g})[0]

onnx_modules/V220_novq_dev/models_onnx.py

@@ -6,7 +6,6 @@ from torch.nn import functional as F
 import commons
 import modules
 from . import attentions_onnx
-from vector_quantize_pytorch import VectorQuantize
 
 from torch.nn import Conv1d, ConvTranspose1d, Conv2d
 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm