Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ Moshi is a speech-text foundation model and full-duplex spoken dialogue framewor
|
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
|
|
|
|
|
|
| 16 |
### Model Description
|
| 17 |
|
| 18 |
Moshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics.
|
|
|
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
| 16 |
+
MLX version for Mac quantized with 8-bits precision.
|
| 17 |
+
|
| 18 |
### Model Description
|
| 19 |
|
| 20 |
Moshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics.
|