Comments (5)
Sorry for such a late reply, I believe the Session1\dialog\EmoEvaluation directory has the correct .txt files
from emotionalconversionstargan.
@WestbrookZero do you know if this solved your issue? Thanks
from emotionalconversionstargan.
I think the directory structure that comes with IEMOCAP is different to what run_preprocessing.py
expects, so I had to make changes to the script get it to look in the correct places. Below are the changes I made:
diff --git a/run_preprocessing.py b/run_preprocessing.py
index cc969c2..63e49f8 100644
--- a/run_preprocessing.py
+++ b/run_preprocessing.py
@@ -30,28 +30,36 @@ def copy_files(iemocap_dir, output_dir):
if not os.path.exists(annotations_output_dir):
os.mkdir(annotations_output_dir)
- filenames = []
- specs = []
- mels = []
- labels = []
- conts = []
- conts_dis = []
- speakers = []
for session in os.listdir(iemocap_dir):
+ if not session.startswith("Session"):
+ continue
+
+ session_dir = os.path.join(iemocap_dir, session)
+
+ annotations_dir = os.path.join(session_dir, "dialog", "EmoEvaluation")
+ for filename in os.listdir(annotations_dir):
+ if not filename.endswith(".txt"):
+ continue
+
+ src_file = os.path.join(annotations_dir, filename)
+ dest_file = os.path.join(annotations_output_dir, filename)
+ if not os.path.exists(dest_file):
+ copyfile(src_file, dest_file)
- if not session == ".DS_Store":
- session_dir = os.path.join(iemocap_dir, session)
- for foldername in os.listdir(session_dir):
+ wav_dir = os.path.join(session_dir, "sentences", "wav")
+ for foldername in os.listdir(wav_dir):
+ if not foldername.startswith("Ses"):
+ continue
- subsession_dir = os.path.join(session_dir, foldername)
- if not foldername == ".DS_Store":
- for filename in os.listdir(subsession_dir):
+ subsession_dir = os.path.join(wav_dir, foldername)
+ for filename in os.listdir(subsession_dir):
+ if not filename.endswith(".wav"):
+ continue
- if not filename == ".DS_Store":
- src_file = os.path.join(subsession_dir, filename)
- dest_file = os.path.join(annotations_output_dir, filename) if foldername == "Annotations" else os.path.join(audio_output_dir, filename)
- if not os.path.exists(dest_file):
- copyfile(src_file, dest_file)
+ src_file = os.path.join(subsession_dir, filename)
+ dest_file = os.path.join(audio_output_dir, filename)
+ if not os.path.exists(dest_file):
+ copyfile(src_file, dest_file)
print(session + " completed.")
from emotionalconversionstargan.
Yes I was aware that the version of the dataset I was using was already restructured in some way. I will look into this issue and possibly update the repo following your changes. Would you be able to create a pull request for this?
from emotionalconversionstargan.
@max-elliott I've created #8 with those changes.
from emotionalconversionstargan.
Related Issues (7)
- Detailed instructions to train HOT 2
- Is there a pretrained model we can download? HOT 2
- Does "<path/to/model_checkpoint.ckpt>" mean "./checkpoints/model_step2/30000",when perform conversion
- num_emos should be 4 not 3 HOT 3
- UnboundLocalError: local variable 'dimensions_dis' referenced before assignment
- Learned speech pronunciation problems
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from emotionalconversionstargan.