cosmetic improvements

README.md

@@ -7,8 +7,8 @@
 # create and activate python venv
 python3 -m venv env
 source ./env/bin/activate
-python -m pip install -r requirements.txt  # current versions
-# python -m pip install -r requirements_freeze.txt
+python -m pip install -r requirements.txt  # latest versions
+# python -m pip install -r requirements_freeze.txt  # specific versions
 ```
 
 ``` bash
@@ -17,15 +17,15 @@ source ./env/bin/activate
 python src/dataset_init.py
 ```
 
-This will download VCTK and resample it to 16kHz, create the train/test split and remove speakers p280 and p315.
+This will download VCTK, resample it to 16kHz, create the train/test split and remove speakers p280 and p315.
 
 
 ## Training
 
-For two-step trainings, first run the `train[...]_step_1.py`. This creates a run dir in `runs/[...]_step_1`.
-The resulting `state_dict` from step 1 has to be passed to `train_[...]_step_2.py`
+For two-step trainings, first run the `train[...]_step_1.py`. This creates a run directory in `runs/[...]_step_1` in which training metrics and state_dict snapshots are stored.
+A `state_dict` from step 1, typically the latest one, has to be passed to `train_[...]_step_2.py`
 
-`train_all.py` automates this process and trains all models in 2-3 days on an Nvidia 3070 GPU.
+`train_all.py` automates this process and trains all models in about 2-4 days on a single GPU.
 
 ## Inference