v1.2.0

Release commit for v1.2.0
tarepan · Oct 24, 2023 · ed25eac · ed25eac
2 parents 5cf009f + 0824824
commit ed25eac
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -7,7 +7,7 @@
 Predict subjective speech score with only 2 lines of code, with various MOS prediction systems.
 
 ```python
-predictor = torch.hub.load("tarepan/SpeechMOS:v1.1.0", "utmos22_strong", trust_repo=True)
+predictor = torch.hub.load("tarepan/SpeechMOS:v1.2.0", "utmos22_strong", trust_repo=True)
 score = predictor(wave, sr)
 # tensor([3.7730]), good quality speech!
 ```
@@ -20,19 +20,19 @@ import torch
 import librosa
 
 wave, sr = librosa.load("<your_audio>.wav", sr=None, mono=True)
-predictor = torch.hub.load("tarepan/SpeechMOS:v1.1.0", "utmos22_strong", trust_repo=True)
+predictor = torch.hub.load("tarepan/SpeechMOS:v1.2.0", "utmos22_strong", trust_repo=True)
 score = predictor(torch.from_numpy(wave).unsqueeze(0), sr)
 # tensor([3.7730])
 ```
 
 ## How to Use
 SpeechMOS use `torch.hub` built-in model loader, so no needs of library import😉  
-(As general dependencies, SpeechMOS requires Python=>3.10, `torch` and `torchaudio`.)  
+(As general dependencies, SpeechMOS requires Python=>3.8, `torch` and `torchaudio`.)  
 
 First, instantiate a MOS predictor with model specifier string:
 ```python
 import torch
-predictor = torch.hub.load("tarepan/SpeechMOS:v1.1.0", "<model_specifier>", trust_repo=True)
+predictor = torch.hub.load("tarepan/SpeechMOS:v1.2.0", "<model_specifier>", trust_repo=True)
 ```
 
 Then, pass tensor of speeches :: `(Batch, Time)`:

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "speechmos"
-version = "1.1.0"
+version = "1.2.0"
 description = "Easy-to-Use Speech MOS predictors 🎧"
 authors = ["tarepan"]
 readme = "README.md"