# Before Start > - The model was trained on a very short dataset, taken from an audio extract of a video showing what the characters' voices would sound like if French dubbers were involved ! > - Even if this model is "Fan-Dub", the fact remains that the person lending her voice is a professional dubbing artist. > - Of course, with the little information given by the dataset I was able to obtain (tiny bits of a demo tape), it's obvious that the model won't be perfect ! > - I'll try to do the other voices you can hear in the video (bearing in mind that some have more extensive lines of dialogue). > - A model just for fun. # Last Update : <t:1705019120:R> > - **Model URL :** > - https://huggingface.co/rayzox57/GenshinImpact_RVC/resolve/main/Paimon_FanDub_FR_v2_Ov2_850e.zip > - **Version :** > - <a:firev2:1167361499149381662> RVC V2.0 - Ov2 Super > - **Pitch Extraction Algorithm :** > - RMVPE > - **Epochs - Steps :** > - 850 - 2.55k > - **Dataset :** > - ~ 00:00:16 [ Et si GENSHIN IMPACT avait des VOIX FRANÇAISES ? | RE: TAKE ] > - **Recommended Usage :** > - Speech > - **Search Feature Ratio :** > - 0.75 > - **Pitch :** > - ( +12 = Woman ) > - You can adjust if you find better version # Previews : > - **Preview_TTS_VF.wav :** > - *Provide* : TTS - ElevenLabs v1 - Grace FR > - *Contains External Effects* : No > - *Pitch* : +12 > - *Feature Ratio* : 0.75 > - *Info* : As the character is "reputed" to be very colorful as far as his voice is concerned, you'll understand that it's hard to get a satisfactory result with a TTS that doesn't really offer acting > > - **Preview_TTS_En.wav :** > - *Provide* : TTS - ElevenLabs v1 - Grace EN > - *Contains External Effects* : No > - *Pitch* : +12 > - *Feature Ratio* : 0.75 > - *Info* : Just for fun

Reference : https://youtu.be/dYuCKN9O0I0?si=8NVgsQdCoxJGfKU9&t=345