metavoice-1B
#10
by
pranavred
- opened
README.md
CHANGED
|
@@ -21,13 +21,9 @@ We’re releasing MetaVoice-1B under the Apache 2.0 license, *it can be used wit
|
|
| 21 |
## Usage
|
| 22 |
See [Github](https://github.com/metavoiceio/metavoice-src) for the latest usage instructions.
|
| 23 |
|
| 24 |
-
## Finetuning
|
| 25 |
-
|
| 26 |
-
See [Github](https://github.com/metavoiceio/metavoice-src?tab=readme-ov-file#finetuning) for the latest finetuning instructions.
|
| 27 |
-
|
| 28 |
## Soon
|
| 29 |
-
- Long form
|
| 30 |
-
-
|
| 31 |
|
| 32 |
## Architecture
|
| 33 |
We predict EnCodec tokens from text, and speaker information. This is then diffused up to the waveform level, with post-processing applied to clean up the audio.
|
|
|
|
| 21 |
## Usage
|
| 22 |
See [Github](https://github.com/metavoiceio/metavoice-src) for the latest usage instructions.
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Soon
|
| 25 |
+
- Long form TTS
|
| 26 |
+
- Fine-tuning code
|
| 27 |
|
| 28 |
## Architecture
|
| 29 |
We predict EnCodec tokens from text, and speaker information. This is then diffused up to the waveform level, with post-processing applied to clean up the audio.
|