replace frd repo

app.py

@@ -53,8 +53,8 @@ sys.path.append('{}/third_party/Matcha-TTS'.format(ROOT_DIR))
 
 from huggingface_hub import snapshot_download
 snapshot_download('FunAudioLLM/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
-snapshot_download('FunAudioLLM/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
-os.system('cd pretrained_models/CosyVoice-ttsfrd/ && unzip resource.zip && pip install ttsfrd_dependency-0.1-py3-none-any.whl && pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl && tar -xvf resource.tar')
+snapshot_download('kemuriririn/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
+os.system('cd pretrained_models/CosyVoice-ttsfrd/ && pip install ttsfrd_dependency-0.1-py3-none-any.whl && pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl && unzip resource.zip -d .')
 
 from cosyvoice.cli.cosyvoice import CosyVoice2
 from cosyvoice.utils.file_utils import load_wav, logging

requirements.txt

@@ -4,9 +4,12 @@
 --trusted-host pypi.nvidia.com
 audioseal==0.1.4
 conformer==0.3.2
-diffusers==0.27.2
+diffusers==0.29.0
 funasr==1.2.0
 gdown==5.1.0
+gradio==5.4.0
+grpcio==1.57.0
+grpcio-tools==1.57.0
 huggingface-hub==0.23.5
 hydra-core==1.3.2
 HyperPyYAML==1.2.2
@@ -14,26 +17,28 @@ inflect==7.3.1
 librosa==0.10.2
 lightning==2.2.4
 matplotlib==3.7.5
-modelscope==1.17.1
+modelscope==1.20.0
 networkx==3.1
 omegaconf==2.3.0
 onnx==1.16.0
-onnxruntime-gpu==1.20.1
-onnxconverter_common==1.14.0
+onnxruntime-gpu==1.18.0; sys_platform == 'linux'
+onnxruntime==1.18.0; sys_platform == 'darwin' or sys_platform == 'win32'
 openai-whisper==20231117
-protobuf==3.20.2
+protobuf==4.25
+pyarrow==18.1.0
 pydantic==2.7.0
+pyworld==0.3.4
 rich==13.7.1
 soundfile==0.12.1
 tensorboard==2.14.0
-tensorrt-cu12==10.0.1
-tensorrt-cu12-bindings==10.0.1
-tensorrt-cu12-libs==10.0.1
+tensorrt-cu12==10.0.1; sys_platform == 'linux'
+tensorrt-cu12-bindings==10.0.1; sys_platform == 'linux'
+tensorrt-cu12-libs==10.0.1; sys_platform == 'linux'
+torch
+torchaudio
 transformers==4.40.1
 uvicorn==0.30.0
 wget==3.2
 fastapi==0.111.0
 fastapi-cli==0.0.4
-WeTextProcessing==1.0.3
-torchaudio
-torch
+WeTextProcessing==1.0.3