FR_M1 mixed excitation: less buzz (same weights, new vocoder setting, ONNX and samples)
73f7700 verified |
Download README.md from DanielSuncost/tiny-voca-fr: direct link, hf CLI and curl.
- Browser
- Download file 2.78 kB
-
https://huggingface.co/DanielSuncost/tiny-voca-fr/resolve/main/README.md
- Command line
-
hf download hf://DanielSuncost/tiny-voca-fr/README.md
-
curl -L -o README.md https://huggingface.co/DanielSuncost/tiny-voca-fr/resolve/main/README.md
2.78 kB
| license: apache-2.0 | |
| language: | |
| - fr | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - tts | |
| - onnx | |
| - tiny | |
| base_model: n4ze3m/tiny-voca | |
| # tiny-voca-fr | |
| A small standard French text-to-speech model: two voices, 4.5M parameters, | |
| 18 MB with the waveform generator included. It runs on a CPU or in the browser. | |
| French port of [tiny-voca](https://huggingface.co/n4ze3m/tiny-voca). | |
| [Code](https://github.com/DanielSuncost/tiny-voca-fr) · [Demo](https://www.suncostlabs.com/tinyvocafr) | |
| ## Voices | |
| | Voice | Description | Samples | | |
| |---|---|---| | |
| | `FR_F1` | Female, mid-forties, warm and clear | `samples/FR_F1-*.wav` | | |
| | `FR_M1` | Male, mid-fifties, deep and calm | `samples/FR_M1-*.wav` | | |
| ## Files | |
| | File | | | |
| |---|---| | |
| | `tiny-voca-fr.pt` | PyTorch inference checkpoint | | |
| | `config.json` | Model configuration | | |
| | `onnx/model.onnx` | ONNX export (phoneme ids in, 24 kHz audio out) | | |
| | `onnx/model.json` | Voices, phoneme symbols and ONNX inputs | | |
| | `samples/` | Four sentences per voice | | |
| ## Usage | |
| ```bash | |
| git clone https://github.com/DanielSuncost/tiny-voca-fr.git && cd tiny-voca-fr | |
| pip install -e . && sudo apt install espeak-ng | |
| hf download DanielSuncost/tiny-voca-fr --local-dir weights | |
| TINY_VOCA_LANGUAGE=fr python -m tiny_voca.infer --checkpoint weights/tiny-voca-fr.pt \ | |
| --voice FR_F1 --text "Bonjour, comment allez-vous ?" --output bonjour.wav | |
| ``` | |
| ONNX inputs: `tokens` and `stress` (int64 `[1, n]`, from the eSpeak NG `fr-fr` | |
| front end in the code repository), `voice` (int64 `[1]`, 0 = FR_F1, 1 = FR_M1), | |
| `speed`, `pitch_shift`, `pitch_range` (float32 `[1]`). Outputs: `audio` | |
| (float32, 24 kHz) and `durations` (frames per token). | |
| ## Training data | |
| Synthetic. Qwen3-TTS 1.7B Base (Apache-2.0) read 9,200 sentences in two voices | |
| designed with Qwen3-TTS VoiceDesign: 8,000 from the Common Voice sentence | |
| collector (CC0) and 1,200 templates for numbers, prices, times and dates. | |
| Clips were screened with Whisper large-v3-turbo and aligned with wav2vec2; | |
| 14.1 hours were used for training (100,000 steps). | |
| ## Results | |
| Whisper large-v3-turbo word error rate: 0% for both voices on unseen | |
| pronunciation test sentences (liaison, h aspiré, nasal vowels, *tu/tout*, | |
| *œuf/œufs*); 0% (FR_F1) and 4.5% (FR_M1, same as the teacher) on held-out test | |
| sentences. | |
| ## Limits | |
| - The male voice is less natural than the female voice. Its vocoder now mixes | |
| noise into half of the pulse power above 1 kHz (mixed excitation, no extra | |
| parameters), which removes most of the earlier mechanical buzz; a faint | |
| trace can remain. Use the current code with these weights: older code loads | |
| them without the mix. | |
| - eSpeak NG misses some liaisons (*comment‿allez*), adds a few false ones, and | |
| reads *fils* (son) as [fil]. | |
| - Two fixed voices. No voice cloning. | |
| ## License | |
| Apache-2.0. | |