Release NVIDIA WakeWord Trainer v17

README.md

@@ -22,7 +22,7 @@ docker pull ghcr.io/tatertotterson/microwakeword:latest
 Tagged releases also publish matching immutable image tags:
 
 ```bash
-docker pull ghcr.io/tatertotterson/microwakeword:v16
+docker pull ghcr.io/tatertotterson/microwakeword:v17
 ```
 
 The release tag must match `VERSION`. Update `WHATS_NEW.md` before tagging; the Docker workflow prepends it to GitHub's automatically generated release notes.
@@ -32,7 +32,7 @@ Python 3.13 TensorFlow build for `sm_120`:
 
 ```bash
 docker pull ghcr.io/tatertotterson/microwakeword:blackwell
-docker pull ghcr.io/tatertotterson/microwakeword:v16-blackwell
+docker pull ghcr.io/tatertotterson/microwakeword:v17-blackwell
 ```
 
 Use the Blackwell image only for RTX 50-series cards. It includes the
@@ -53,9 +53,9 @@ docker run -d \
   ghcr.io/tatertotterson/microwakeword:latest
 ```
 
-Use a version tag such as `ghcr.io/tatertotterson/microwakeword:v16` when you want to pin a known release instead of tracking `latest`.
+Use a version tag such as `ghcr.io/tatertotterson/microwakeword:v17` when you want to pin a known release instead of tracking `latest`.
 For RTX 50-series cards, use `ghcr.io/tatertotterson/microwakeword:blackwell`
-or a pinned tag such as `ghcr.io/tatertotterson/microwakeword:v16-blackwell`
+or a pinned tag such as `ghcr.io/tatertotterson/microwakeword:v17-blackwell`
 in the same `docker run` command.
 
 The flags:

VERSION

@@ -1 +1 @@
-16
+17

WHATS_NEW.md

@@ -1,2 +1,2 @@
-- Fixed a startup crash caused by newer pip-installed NVIDIA cuBLAS and cuDNN namespace packages not providing a module file path.
+- Fixed the training-status endpoint crashing after a training log was created because its log-tail limits were missing.
-- CUDA library discovery now works across both the standard NVIDIA and Blackwell images and safely allows startup when the optional libraries are unavailable.
+- Restored bounded, incremental training-log updates so the UI can continue showing live progress without repeatedly reading the entire log.

tests/test_auto_train.py

@@ -425,6 +425,39 @@ class AutoTrainTests(unittest.TestCase):
         self.assertEqual(trainer.AUTO_TRAIN_STATE["last_stt_device"], "cuda")
         self.assertEqual(trainer.AUTO_TRAIN_STATE["last_stt_compute_type"], "float16")
 
+    def test_train_status_reads_and_increments_training_log_tail(self):
+        log_path = Path(self.tempdir.name) / "training.log"
+        log_path.write_text("first\nsecond\nthird\n", encoding="utf-8")
+        with trainer.STATE_LOCK:
+            original_training = dict(trainer.STATE["training"])
+            trainer.STATE["training"].update(
+                {
+                    "log_path": str(log_path),
+                    "last_sent_tail": [],
+                    "last_log_size": 0,
+                }
+            )
+
+        try:
+            with (
+                patch.object(trainer, "TRAIN_LOG_TAIL_LINES", 2),
+                patch.object(trainer, "TRAIN_LOG_MAX_BYTES", 1024),
+            ):
+                first_status = trainer.train_status()
+                self.assertEqual(first_status["training"]["log_lines"], ["second", "third"])
+                self.assertEqual(first_status["training"]["log_text"], "second\nthird")
+
+                with log_path.open("a", encoding="utf-8") as log_file:
+                    log_file.write("fourth\n")
+
+                next_status = trainer.train_status()
+                self.assertEqual(next_status["training"]["log_lines"], ["third", "fourth"])
+                self.assertEqual(next_status["training"]["log_text"], "fourth")
+        finally:
+            with trainer.STATE_LOCK:
+                trainer.STATE["training"].clear()
+                trainer.STATE["training"].update(original_training)
+
 
 if __name__ == "__main__":
     unittest.main()

trainer_server.py

@@ -70,6 +70,8 @@ PIPER_CATALOG_CACHE_FILE = Path(
         str(DATA_DIR / ".cache" / "piper_voices_catalog.json"),
     )
 ).resolve()
+TRAIN_LOG_TAIL_LINES = int(os.environ.get("REC_TRAIN_LOG_TAIL_LINES", "400"))
+TRAIN_LOG_MAX_BYTES = int(os.environ.get("REC_TRAIN_LOG_MAX_BYTES", str(512 * 1024)))
 
 DATASET_CLEANUP_ARCHIVES = os.environ.get("REC_DATASET_CLEANUP_ARCHIVES", "false").lower() in ("1", "true", "yes", "y")
 DATASET_CLEANUP_INTERMEDIATE = os.environ.get("REC_DATASET_CLEANUP_INTERMEDIATE_FILES", "false").lower() in ("1", "true", "yes", "y")