diff --git a/README.md b/README.md index 5cc8344..3c86f2c 100644 --- a/README.md +++ b/README.md @@ -1,16 +1,11 @@
Start a session, upload your own recorded voice samples, and the app will validate or convert them into the training format used by the existing pipeline.
+Train wake words, review captured clips, and flash ESPHome firmware from one local workspace.
Personal samples are optional. You can train with TTS only, or upload your own audio here and it will be saved into personal_samples/ as 16 kHz mono 16-bit PCM WAV.
WAV, MP3, M4A, FLAC, OGG, AAC, OPUS, and WEBM are all fine when ffmpeg is available. Files already in the correct format are kept as-is.
-Start with a phrase, review your positive and negative sample counts, then launch the training pipeline with a live console so every step is visible.
+personal_samples/.Name the wake phrase and choose the language/voice set used to generate training audio.
+Device-captured positives and reviewed negatives are used when present. Manual samples are managed from the Samples tab.
+Listen to clips sent by your sats, turn good wake-word examples into personal samples, and save false positives as negatives for the next training run.
+Refresh clips from the trainer inbox and keep an eye on how many reviewed negatives and personal samples are ready.
+Approve strong wake-word clips into personal samples, or mark false positives as reviewed negatives.
+Listen to saved positive and negative samples, remove anything that does not belong, or manually import seed recordings when you need a starting point.
+Build a microWakeWords ESPHome firmware template and flash it to a sat over OTA. Auto-detect is best effort; if the device does not show up, enter its IP or hostname manually.
Choose the VoicePE or Sat1 YAML to build from the shared firmware repo.
+Auto-detect a device or enter the OTA target manually.
+These values come from the selected YAML substitutions and are saved for the next flash.
+The ESPHome output opens in the console so you can follow build, upload, and reboot progress.
+Live training output appears here with color-coded console styling.
+Live training output appears here with color-coded console styling.