Hi, I have added voices/glados.onnx and voices/glados.onnx.json from: https://github.com/dnhkng/GlaDOS
I have also added glados: model: voices/glados.onnx speaker: 163 to config/voice_to_speaker.yaml and config/voice_to_speaker.default.yaml
The voice is not generated and the server prints: INFO: 192.168.64.113:37818 - "POST /v1/audio/speech HTTP/1.1" 200 OK Traceback (most recent call last): File "/root/audio/openedai-speech/.venv/bin/piper", line 8, in <module> sys.exit(main()) ^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/__main__.py", line 126, in main for audio_bytes in audio_stream: File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/voice.py", line 123, in synthesize_stream_raw yield self.synthesize_ids_to_raw( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/voice.py", line 166, in synthesize_ids_to_raw audio = self.session.run( ^^^^^^^^^^^^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run return self._sess.run(output_names, input_feed, run_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid input name: sid
OS: debian 12
python: 3.11
curl: curl http://192.168.73.78:8000/v1/audio/speech -H "Content-Type: application/json" -d '{ "model": "tts-1", "input": "The quick brown fox jumped over the lazy dog.", "voice": "glados", "response_format": "mp3", "speed": 1.0 }' > speech.mp3
Hi, I have added
voices/glados.onnx
andvoices/glados.onnx.json
from: https://github.com/dnhkng/GlaDOS I have also addedglados: model: voices/glados.onnx speaker: 163
toconfig/voice_to_speaker.yaml
andconfig/voice_to_speaker.default.yaml
The voice is not generated and the server prints:
INFO: 192.168.64.113:37818 - "POST /v1/audio/speech HTTP/1.1" 200 OK Traceback (most recent call last): File "/root/audio/openedai-speech/.venv/bin/piper", line 8, in <module> sys.exit(main()) ^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/__main__.py", line 126, in main for audio_bytes in audio_stream: File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/voice.py", line 123, in synthesize_stream_raw yield self.synthesize_ids_to_raw( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/piper/voice.py", line 166, in synthesize_ids_to_raw audio = self.session.run( ^^^^^^^^^^^^^^^^^ File "/root/audio/openedai-speech/.venv/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run return self._sess.run(output_names, input_feed, run_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid input name: sid
OS: debian 12 python: 3.11 curl:
curl http://192.168.73.78:8000/v1/audio/speech -H "Content-Type: application/json" -d '{ "model": "tts-1", "input": "The quick brown fox jumped over the lazy dog.", "voice": "glados", "response_format": "mp3", "speed": 1.0 }' > speech.mp3
Thank you.