OptiSpeech ConvNext TTS Es CO Marcia v0

--- language: - es license: apache-2.0 tags: - audio - text-to-speech - onnx - optispeech - convnext-tts - spanish datasets: - bookbot/es-CO-Marcia inference: false --- # OptiSpeech ConvNext-TTS es-CO-Marcia v0 OptiSpeech ConvNext-TTS es-CO-Marcia v0 is a Spanish single-speaker text-to-speech ONNX export trained with the OptiSpeech framework. The speaker is Marcia, targeting Colombian Spanish (`es-CO`). This model uses the OptiSpeech Spanish `TextProcessor` at inference time. No separate `gruut_*_symbols.py` file is needed for this export. ## Model | Model | ONNX file | Config | SR (Hz) | Mel range (Hz) | FFT / Hop / Win | Inference scales | | --- | --- | --- | --- | --- | --- | --- | | `bookbot/OptiSpeech-ConvNext-TTS-es-CO-Marcia-v0` | `convnext-tts-es-CO-Marcia-v0.onnx` | `config_tree.log` | 44100 | 0-22050 | 2048 / 512 / 2048 | d=1.1, p=1.6, e=1.2 | ## Files - `convnext-tts-es-CO-Marcia-v0.onnx`: ONNX text-to-waveform export. - `config_tree.log`: rendered training configuration. - `training_metadata/config.yaml`: Hydra training config. - `training_metadata/hydra.yaml`: Hydra runtime config. - `training_metadata/overrides.yaml`: command-line overrides for the source run. - `onnx_inference_es.py`: Spanish ONNX inference helper. ## Training Source This export was staged from: ```text logs/train/es_speaker_ddp/convnext-tts-ES-Marcia.onnx logs/train/es_speaker_ddp/runs/2026-06-22_18-42-17/ ``` The source run used: ```text experiment=es_speaker_ddp ckpt_path=logs/train/es_speaker_ddp/resume.ckpt ``` ## ONNX Inference Run inference from an OptiSpeech checkout with the Spanish text processor dependencies installed: ```sh source .venv/bin/activate uv sync --extra es python onnx_inference_es.py \ --model_path convnext-tts-es-CO-Marcia-v0.onnx \ --input "Hola, esta es una prueba de síntesis de voz en español colombiano." \ --output_path outputs \ --output_name marcia_v0.wav ``` The ONNX model expects: - `x`: phoneme/token IDs from `optispeech.text.TextProcessor(languages=["es"])` - `x_lengths`: input sequence lengths - `scales`: duration, pitch, and energy factors The helper script handles text normalization, Spanish phonemization/tokenization, ONNXRuntime execution, and WAV writing. ## Framework - OptiSpeech - ONNXRuntime - PyTorch / Lightning training stack

Source context: 0 downloads · 0 likes · Pipeline text-to-speech · Repo bookbot/OptiSpeech-ConvNext-TTS-es-CO-Marcia-v0