| --- |
| language: |
| - fa |
| license: mit |
| pipeline_tag: text-to-speech |
| base_model: rhasspy/piper-voices |
| library_name: piper |
| model_type: text-to-speech |
| tags: |
| - audio |
| - text-to-speech |
| - piper |
| - vits |
| - persian |
| - farsi |
| - fonnely |
| pretty_name: Gooya RizehPizeh v1.5 |
| --- |
| |
| # Gooya RizehPizeh v1.5 |
|
|
| Persian (Farsi) text-to-speech voice **"gooya-fa"** for [Piper](https://github.com/rhasspy/piper), |
| trained with the AvaSanj/Negara improved G2P front end. Single-speaker, 22050 Hz, `phoneme_type: text` |
| (no espeak-ng required at inference time). |
|
|
| ## Provenance |
|
|
| - **Original model:** [Piper](https://github.com/rhasspy/piper) VITS, warm-started from the **Mana Persian Piper** |
| checkpoint (`epoch=6012-step=4203520.ckpt`, sdp enabled). This model is therefore a **fine-tune of Piper**, |
| continuing from a mature Persian training run rather than training from scratch. |
| - **Front end:** phonemic input produced by **Negara v7.1** G2P (grapheme-to-phoneme), with phoneme ids |
| mapped through the Mana 256-symbol inventory (157 real phonemes). |
| - **Training data:** AvaSanj **clean-core v2** — 102,584 utterances whose phoneme labels were rebuilt by the |
| OOF (out-of-fold) listener policy: |
| - `oof_listener_winner` … 48,656 (OOF AvaSanj ASR margin ≥ 0.1) |
| - `stored_audio_prompt` … 42,244 (unchanged approved prompts) |
| - `three_listener_consensus` … 11,342 (unanimous multi-listener rows) |
| - `human_override` … 41 |
| - `human_reviewed_v71_overlay` … 301 |
| - 28,253 rows changed vs. the stored prompt (the G2P improvement delivered by this project). |
| - **Split:** 5% validation, `num_test_examples: 0`. |
|
|
| ## Model |
|
|
| - Generator parameters: **23,663,792** (~23.7 M) |
| - Architecture (Piper/VITS): `hidden_channels 192`, `filter_channels 768`, `inter_channels 192`, |
| 6 flow layers, 2 attention heads, `resblock 2`, upsampling rates `[8, 8, 4]` (upsample initial channel 256), |
| `mel_channels 80`, `use_sdp true`, `num_symbols 256`, `num_speakers 1`. |
| - Vocab: 157 phoneme tokens (`text` phoneme type, Mana id map with `^`/`_`/`$` control tokens). |
|
|
| ## Inference |
|
|
| ```bash |
| echo "salAm olAqe aziz hAlet Cetore" | \ |
| piper -m gooya-fa.onnx -c gooya-fa.onnx.json -f output.wav |
| ``` |
|
|
| Inference-scales baked into `gooya-fa.onnx.json`: `noise_scale 0.667`, `length_scale 1.0`, `noise_w 0.8`; |
| sample rate `22050` Hz; `espeak.voice: fa`; `phoneme_type: text`. |
|
|
| ## Files |
|
|
| - `gooya-fa.onnx` — ONNX model (inference runtime) |
| - `gooya-fa.onnx.json` — Piper voice/config metadata |
| - `checkpoint/epoch=*-val_mel=*.ckpt` — PyTorch training checkpoint (resumable) |
