Downloads · 30 days
365
46% of all-time downloads
tontate/f5-tts-quebec-french-finetune
f5-tts-quebec-french-finetune is a text-to-speech model from tontate. Use it when you need text read aloud. It is set up for f5-tts. The card lists the license as cc-by-nc-4.0.
A zero-shot voice-cloning TTS checkpoint specialized for Quebec French. Give it a short reference clip of any voice and it clones that voice while applying Québécois pronunciation, prosody, and vocabulary.
Downloads · 30 days
365
46% of all-time downloads
All-time downloads
796
Public
Repo size
21 GB
Likes
2
Public
Click a slice to open those files.
.pt10.8 GB · 86%
From the Hugging Face model README
A zero-shot voice-cloning TTS checkpoint specialized for Quebec French. Give it a short reference clip of any voice and it clones that voice while applying Québécois pronunciation, prosody, and vocabulary.
Finetune of F5-TTS (F5TTS_Base architecture,
vocos vocoder), warm-started from
RASPIAUDIO/F5-French-MixedSpeakers-reduced
and trained on a Québécois-accent-tagged subset of Mozilla Common Voice (fr).
License note: the warm-start base checkpoint is CC-BY-NC-4.0. This finetune inherits that restriction — non-commercial use only. The training data itself is CC0-1.0.
pip install f5-tts
f5-tts_infer-cli \
--model F5TTS_Base \
--ckpt_file model_quebec_v1.safetensors \
--vocab_file vocab.txt \
--ref_audio your_reference.wav \
--ref_text "Transcript of the reference clip." \
--gen_text "Je m'en vais au dépanneur chercher de la liqueur pis des chips."
Download the two required files with:
huggingface-cli download tontate/f5-tts-quebec-french-finetune \
model_quebec_v1.safetensors vocab.txt
Tips: use a clean 3–10 s reference clip; leave --ref_text "" to auto-transcribe it.
The checkpoint clones any voice — a Québécois-accented reference gives the most
consistent results.
Generated with the final checkpoint (voice qc_a); more in samples/.
« Il faut que je stationne mon char devant le dépanneur. »
<audio controls src="https://huggingface.co/tontate/f5-tts-quebec-french-finetune/resolve/main/samples/final_67750/qc_a/00.wav"></audio>
« Fait qu'on a fini par jaser toute la soirée sur la galerie. »
<audio controls src="https://huggingface.co/tontate/f5-tts-quebec-french-finetune/resolve/main/samples/final_67750/qc_a/04.wav"></audio>
« Ça coûte quatre-vingt-dix-sept dollars et trente-cinq sous. »
<audio controls src="https://huggingface.co/tontate/f5-tts-quebec-french-finetune/resolve/main/samples/final_67750/qc_a/08.wav"></audio>
| File | Size | Use |
|---|---|---|
model_quebec_v1.safetensors | 1.35 GB | Recommended for inference — EMA weights only |
model_last.pt | 5.39 GB | Full training checkpoint (model + EMA + optimizer) — for resuming training |
checkpoints/model_9000.pt, checkpoints/model_12000.pt | 5.39 GB each | Intermediate training checkpoints |
vocab.txt | 14 kB | Tokenizer vocab (unchanged from base / F5-TTS default) |
scripts/prep_common_voice_qc.py | — | Dataset preparation script (reproducible) |
dataset/processed_qc_dataset.tar.gz | — | The processed training set |
samples/ | — | Eval-sentence audio (2 voices) + per-checkpoint training-trajectory samples |
model_quebec_v1.safetensors contains exactly the EMA weights of model_last.pt
(bitwise-identical extraction, verified), repackaged for safe, fast loading.
accent metadata. Final set: 11,542 clips, 281 speakers,
12.01 hours (after resample to 24 kHz mono, silence trim, dedup, 1–15 s length
filter). Prep script included in scripts/.samples/training_trajectory/ if you want to compare checkpoints.Evaluated on a 50-sentence Québécois test battery targeting dialect-specific
phenomena (affrication, vowel laxing, /a/–/ɑ/ contrast & diphthongs, QC
lexicon/elisions, numbers, question particles & prosody), synthesized with
3 reference voices, and compared against the warm-start base model
(RASPIAUDIO/F5-French-MixedSpeakers-reduced, France-accented). Scripts and
the sentence list are in scripts/eval/.
| Metric | Base (France) | This model (Québec) |
|---|---|---|
| WER ↓ (faster-whisper large-v3) | 0.067 | 0.077 |
| CER ↓ | 0.041 | 0.043 |
| Speaker similarity ↑ (ECAPA cosine) | 0.479 | 0.675 |
| Accent probe: mean P(Québec) ↑ | 0.17 | 0.40 |
Caveats: reference clips are drawn from the training corpus (speaker-similarity numbers are in-domain); the accent probe is a proxy, not a listening test; number-heavy sentences are hardest for both models — write numbers out in words.