Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- neuphonic/emilia-yodas-english-neucodec
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-to-speech
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
# Echolancer Stage 2 Base
|
| 12 |
+
|
| 13 |
+
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.
|
| 14 |
+
|
| 15 |
+
The training objective was standard next-token prediction on concatenated text-audio tokens.
|
| 16 |
+
|
| 17 |
+
# Code
|
| 18 |
+
For more information including a Colab notebook, see [the repository](https://github.com/ZDisket/Echolancer).
|