ARM64 Compatibility, dependencies fix

Author: remsky

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 Notable changes to this project will be documented in this file.
 
+## [v0.2.0post1] - 2025-02-07
+- Fix: Building Kokoro from source with adjustments, to avoid CUDA lock 
+- Fixed ARM64 compatibility on Spacy dep to avoid emulation slowdown
+- Added g++ for Japanese language support
+- Temporarily disabled Vietnamese language support due to ARM64 compatibility issues
+
 ## [v0.2.0-pre] - 2025-02-06
 ### Added
 - Complete Model Overhaul:

api/src/models/v1_0/config.json

@@ -1,37 +1,15 @@
 {
   "istftnet": {
-    "upsample_kernel_sizes": [
-      20,
-      12
-    ],
-    "upsample_rates": [
-      10,
-      6
-    ],
+    "upsample_kernel_sizes": [20, 12],
+    "upsample_rates": [10, 6],
     "gen_istft_hop_size": 5,
     "gen_istft_n_fft": 20,
     "resblock_dilation_sizes": [
-      [
-        1,
-        3,
-        5
-      ],
-      [
-        1,
-        3,
-        5
-      ],
-      [
-        1,
-        3,
-        5
-      ]
-    ],
-    "resblock_kernel_sizes": [
-      3,
-      7,
-      11
+      [1, 3, 5],
+      [1, 3, 5],
+      [1, 3, 5]
     ],
+    "resblock_kernel_sizes": [3, 7, 11],
     "upsample_initial_channel": 512
   },
   "dim_in": 64,
@@ -68,13 +46,13 @@
     "“": 14,
     "”": 15,
     " ": 16,
-    "̃": 17,
+    "\u0303": 17,
     "ʣ": 18,
     "ʥ": 19,
     "ʦ": 20,
     "ʨ": 21,
     "ᵝ": 22,
-    "ꭧ": 23,
+    "\uAB67": 23,
     "A": 24,
     "I": 25,
     "O": 31,

docker/cpu/Dockerfile

@@ -1,4 +1,4 @@
-FROM --platform=$BUILDPLATFORM python:3.10-slim 
+FROM python:3.10-slim 
 
 # Install dependencies and check espeak location
 RUN apt-get update && apt-get install -y \
@@ -8,10 +8,11 @@ RUN apt-get update && apt-get install -y \
     libsndfile1 \
     curl \
     ffmpeg \
+    g++ \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* \
     && mkdir -p /usr/share/espeak-ng-data \
-    && ln -s /usr/lib/x86_64-linux-gnu/espeak-ng-data/* /usr/share/espeak-ng-data/
+    && ln -s /usr/lib/*/espeak-ng-data/* /usr/share/espeak-ng-data/
 
 # Install UV using the installer script
 RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
@@ -57,4 +58,4 @@ RUN if [ "$DOWNLOAD_MODEL" = "true" ]; then \
 
 ENV DEVICE="cpu"
 # Run FastAPI server through entrypoint.sh
-CMD ["./entrypoint.sh"]
+CMD ["./entrypoint.sh"]

pyproject.toml

@@ -33,10 +33,10 @@ dependencies = [
     "matplotlib>=3.10.0",
     "mutagen>=1.47.0",
     "psutil>=6.1.1",
-    "kokoro==0.7.9",
-    'misaki[en,ja,ko,zh,vi]==0.7.9',
-    "spacy>=3.7.6",
-    "en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl"
+    "kokoro @ git+https://github.com/hexgrad/kokoro.git@31a2b6337b8c1b1418ef68c48142328f640da938",
+    'misaki[en,ja,ko,zh] @ git+https://github.com/hexgrad/misaki.git@ebc76c21b66c5fc4866ed0ec234047177b396170',
+    "spacy==3.7.2",
+    "en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl"
 ]
 
 [project.optional-dependencies]
@@ -51,7 +51,6 @@ test = [
     "pytest-cov==4.1.0",
     "httpx==0.26.0",
     "pytest-asyncio==0.23.5",
-    "gradio>=5",
     "openai>=1.59.6",
 ]