Document model file size and parameter count availability
Browse files
README.md
CHANGED
|
@@ -39,6 +39,9 @@ The measurements below are for ESP32-S3 N16R8 at 240 MHz with ESP-IDF 5.5.6. Res
|
|
| 39 |
| First PCM | 0.27–0.32 seconds from invocation, not speaker playback latency |
|
| 40 |
| Memory | 2.63 MB PSRAM plus about 1 KB internal RAM, or 151 KB internal RAM without PSRAM; task stack, DMA and application memory are extra |
|
| 41 |
| Flash | About 2.6 MB for library, model and dictionary; fits within 4 MB Flash subject to application and partition needs |
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
See the [performance details](https://github.com/LingCoreX-AI/LingTTS/blob/main/docs/资源与性能.md) and [integration guide](https://github.com/LingCoreX-AI/LingTTS/blob/main/docs/集成指南.md) (Chinese).
|
| 44 |
|
|
|
|
| 39 |
| First PCM | 0.27–0.32 seconds from invocation, not speaker playback latency |
|
| 40 |
| Memory | 2.63 MB PSRAM plus about 1 KB internal RAM, or 151 KB internal RAM without PSRAM; task stack, DMA and application memory are extra |
|
| 41 |
| Flash | About 2.6 MB for library, model and dictionary; fits within 4 MB Flash subject to application and partition needs |
|
| 42 |
+
| Model file | About 1.83 MB for one base voice; the optional second voice model is also about 1.83 MB |
|
| 43 |
+
|
| 44 |
+
The deployed model is quantized and packaged; a verified parameter count is not currently published. File size should not be read as parameter count.
|
| 45 |
|
| 46 |
See the [performance details](https://github.com/LingCoreX-AI/LingTTS/blob/main/docs/资源与性能.md) and [integration guide](https://github.com/LingCoreX-AI/LingTTS/blob/main/docs/集成指南.md) (Chinese).
|
| 47 |
|