Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -8,6 +8,11 @@ base_model: spotify/basic-pitch
|
|
| 8 |
|
| 9 |
# Basic Pitch — LiteRT (CompiledModel GPU) music transcription
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
[Basic Pitch](https://github.com/spotify/basic-pitch) (Spotify, ICASSP 2022, Apache-2.0)
|
| 12 |
re-authored to a **GPU-native** LiteRT `.tflite` — **including the conv-based CQT front-end**
|
| 13 |
(9 octaves, shared 36×256 kernel banks, lowpass downsample chain, no FFT). Bit-exact torch
|
|
|
|
| 8 |
|
| 9 |
# Basic Pitch — LiteRT (CompiledModel GPU) music transcription
|
| 10 |
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
*Audio input → note posteriorgram (MIDI pitch × time) from the on-device model.*
|
| 15 |
+
|
| 16 |
[Basic Pitch](https://github.com/spotify/basic-pitch) (Spotify, ICASSP 2022, Apache-2.0)
|
| 17 |
re-authored to a **GPU-native** LiteRT `.tflite` — **including the conv-based CQT front-end**
|
| 18 |
(9 octaves, shared 36×256 kernel banks, lowpass downsample chain, no FFT). Bit-exact torch
|