|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- neuphonic/emilia-yodas-english-neucodec |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-to-speech |
|
|
--- |
|
|
|
|
|
|
|
|
# Echolancer Stage 2 Base |
|
|
|
|
|
This is a TTS model pretrained on the pre-tokenized Emilia dataset. Since there's no speaker conditioning, the speaker is random at inference. This model has 550M parameters and it was trained from scratch on a single AMD Instinct MI300X for ~4 days with the ROCm PyTorch Training v25.7 container. |
|
|
|
|
|
The training objective was standard next-token prediction on concatenated text-audio tokens. |
|
|
|
|
|
# Code |
|
|
For more information including a Colab notebook, see [the repository](https://github.com/ZDisket/Echolancer). |
