-
Extracting phonemes and cleaning existing data.
-
I tried the demo of espeak-ng with the sentence
```console
שלום לכולם. זה בדיקה עם התוכנה כדי לדעת שהיא מפיקה צלילים נכונים.
```
Which produced
```console
Sal'om lXvlm
zh bdik'a 'im htvX…
-
- Find audio source
- Make sure we can legally use said audio
- Add them to project in some capacity
-
Hi!
I'm trying to train RVC models for a range of dialects in my country. I live in South Africa.
I'm struggling with click-consonant phonemes.
These African language sounds are not understo…
-
I'm training the GPT-SoVITS GPT S1 model on a new language. I've made the following modifications to support the new language:
Added new phonemes in symbol2.py
Extended the text embedding dimensio…
-
Hello,
Thank you for releasing the MaskGCT project. The sound quality is great.
In the english model, can you pass phonemes directly to the model for pronunciation?
Thank you
-
Based on the value of POT_PHONEME:
- Choose from a set of predetermine phonemes (there are like 150)
- Translate that into a MIDI SysEx message
- Send it to the evy1 whenever the pot value change…
-
Hi. I have a phoneme-based Zipformer model.
Before this [PR](https://github.com/k2-fsa/sherpa-onnx/pull/828), I was able to apply hotwords encoding for phoneme sequences, e.g. `ɪ z/dʒ ʌ s t/b ɛ s t…
w11wo updated
5 months ago
-
I have combined the phoneme sets for all three langauges,
English, Chinese, Japanese and started fine tuning using a datset comprised of all three speech languages
The base model I use is the chine…
-
Hello! If I understand correctly, then the g2p tool that uses the symbol_set specified in your repository cannot be obtained, right? You say that you can use a different kind of phonemes for training …