Question about accent and .safetensors request
Hello good morning.
Thank you very much for the contribution. Could you please indicate what accent is obtained with this model?
On the other hand, it would be incredible if you could provide it in .safetensors format - I have been trying to convert the .pt file into safetensor for two days but my programming knowledge is zero and I can't do it.
Thank you very much again!
Hello, thanks for your question! There is another model in huggingface that was trained on a very similar database for more time, so it is better (https://huggingface.co/jpgallegoar/F5-Spanish/tree/main) this model has a safetensors version. The .pt is the same file but since it has no "compression" it can be used to continue training the model. Both models used audio from many different spanish accents, so the resulting accent is none in particular. And in general the results are not very good because there is not a lot of databases that have "clean" spanish audio, so the training is limited to a sample of around 120 hours of audio, which is really not enough.
Thank you very much for your detailed response. All the best!