Where is #Select Reference Language, #Select Synthesized Language? I cant find it when running localy
Hey, I have some feedback about the multilanguage model. Can you help me understand this? When I’m using it locally on Pinokio, I don’t see the options to choose:
#Select Reference Language
#Select Synthesized Language
These options are available only on Hugging Face: https://huggingface.co/spaces/Gregniuki/f5-tts_Polish_English_German
Because I can’t select the input and output languages, the model isn’t generating proper audio. Am I doing something wrong, perhaps? I’d be very grateful for help.
I’m attaching screenshots to better explain the issue.
It seems to me that you need to clone the repo from Hugging Face. I did that, and it works because the original F5 doesn't have eSpeak, etc. You would have to change a lot in the code.
Iam super basic with coding.
I am trying to use your Polish model 1200000 on Pinokio. My referance audio is Polish ( Under 10sec) and I do Polish transcription. But for some reason I recive back just a mumbling.
Any idea what am I doing wrong, I tried to use multi model and 500000 as well. For some reason I cant generate anything with proper polish voice :/
I’d be very grateful for help.
I’m attaching screenshot
I have the same issue with english as well. I cant understand why its mumbling
I don’t use Pinokio, so I can’t help. I just downloaded the repo from Hugging Face and ran it. If you’re changing the model, you also need to update the vocab. There was a recent update to version 1.0, and models from before 1.0 were generating gibberish and unclear sound. You need to use the new model.
I'm also from Poland, greetings! ;)
Hej Hobis! dzięki za odpowiedź,
Moglbys mi tylko w zdaniu czy dwoch napisac jak najlepiej odpalic taki model poza Pinokio? Ogolnie jestem swiezynka jesli chodzi o kodowanie ale mam Visual Studio Code i nawet pisze jakis program na pythona.
Czy jest moze jakies srodowisko czy program ktory bys polecil abym mogl odpalic ten F5 TTS?
Wspominasz ze cos dostalo updata do 1.0, o ktorym programie mowisz?
Bo poprzez pinokio odpalam standartowy angielski F5 TTS i wszystko genereuje dobrze.
Dopiero kiedy przelaczam na custom i dodaje twoj model + vocab to zaczyna memlac.
Pozdrawiam z Poznania :)
wich repo? can you send the link please? gretings from germany