-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
642 additions
and
644 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,61 +1,61 @@ | ||
| """This file converts transcript to a txt file that can be read by the unity. | ||
| This script is meant to be run separately. | ||
| This file expects JSON files. jsons_path variable must be manually changed to the appropriate directory. | ||
| The expected structure of the original JSON file is as follow: | ||
| Subtitles are expected to be contained in a JSON file with the format: | ||
| { | ||
| 'alternative': | ||
| []: # only the first element contains the following: | ||
| { | ||
| 'words': [ | ||
| { | ||
| 'start_time': '0.100s', | ||
| 'end_time': '0.500s', | ||
| 'word': 'really' | ||
| }, | ||
| { <contains more of these structured elements> } | ||
| ], | ||
| <other data> | ||
| } | ||
| } | ||
| Note: JSON uses double-quotes instead of single-quotes. Single quotes are used for doc-string reasons. | ||
| The files are saved in a new folder in the jsons_path directory named 'Unity'. | ||
| """ | ||
|
|
||
|
|
||
| import glob | ||
| import os | ||
| from data_utils import SubtitleWrapper | ||
|
|
||
| jsons_path = "/local-scratch/pjomeyaz/GENEA_DATASET/trinityspeechgesture.scss.tcd.ie/data/GENEA_Challenge_2020_data_release/Test_data/Transcripts" | ||
|
|
||
| json_output_path = jsons_path + "/Unity" | ||
| if not os.path.exists(json_output_path): | ||
| os.makedirs(json_output_path) | ||
|
|
||
|
|
||
| json_files = sorted(glob.glob(jsons_path + "/*.json")) | ||
|
|
||
|
|
||
| for jfile in json_files: | ||
| name = os.path.split(jfile)[1][:-5] | ||
| print(name) | ||
|
|
||
| subtitle = SubtitleWrapper(jfile).get() | ||
| str_subtitle = "" | ||
| for word_boundle in subtitle: | ||
| start_time = word_boundle["start_time"][:-1] # Removing 's' | ||
| end_time = word_boundle["end_time"][:-1] # Removing 's' | ||
| word = word_boundle["word"] | ||
| str_subtitle += "{},{},{}\n".format(start_time, end_time, word) | ||
|
|
||
| str_subtitle = str_subtitle[:-1] | ||
|
|
||
| file2write = open(json_output_path + "/" + name + ".txt", "w") | ||
| file2write.write(str_subtitle) | ||
| file2write.flush() | ||
| file2write.close() | ||
|
|
||
| print() | ||
| """This file converts transcript to a txt file that can be read by the unity. | ||
| This script is meant to be run separately. | ||
| This file expects JSON files. jsons_path variable must be manually changed to the appropriate directory. | ||
| The expected structure of the original JSON file is as follow: | ||
| Subtitles are expected to be contained in a JSON file with the format: | ||
| { | ||
| 'alternative': | ||
| []: # only the first element contains the following: | ||
| { | ||
| 'words': [ | ||
| { | ||
| 'start_time': '0.100s', | ||
| 'end_time': '0.500s', | ||
| 'word': 'really' | ||
| }, | ||
| { <contains more of these structured elements> } | ||
| ], | ||
| <other data> | ||
| } | ||
| } | ||
| Note: JSON uses double-quotes instead of single-quotes. Single quotes are used for doc-string reasons. | ||
| The files are saved in a new folder in the jsons_path directory named 'Unity'. | ||
| """ | ||
|
|
||
|
|
||
| import glob | ||
| import os | ||
| from data_utils import SubtitleWrapper | ||
|
|
||
| jsons_path = "/local-scratch/pjomeyaz/GENEA_DATASET/trinityspeechgesture.scss.tcd.ie/data/GENEA_Challenge_2020_data_release/Test_data/Transcripts" | ||
|
|
||
| json_output_path = jsons_path + "/Unity" | ||
| if not os.path.exists(json_output_path): | ||
| os.makedirs(json_output_path) | ||
|
|
||
|
|
||
| json_files = sorted(glob.glob(jsons_path + "/*.json")) | ||
|
|
||
|
|
||
| for jfile in json_files: | ||
| name = os.path.split(jfile)[1][:-5] | ||
| print(name) | ||
|
|
||
| subtitle = SubtitleWrapper(jfile).get() | ||
| str_subtitle = "" | ||
| for word_boundle in subtitle: | ||
| start_time = word_boundle["start_time"][:-1] # Removing 's' | ||
| end_time = word_boundle["end_time"][:-1] # Removing 's' | ||
| word = word_boundle["word"] | ||
| str_subtitle += "{},{},{}\n".format(start_time, end_time, word) | ||
|
|
||
| str_subtitle = str_subtitle[:-1] | ||
|
|
||
| file2write = open(json_output_path + "/" + name + ".txt", "w") | ||
| file2write.write(str_subtitle) | ||
| file2write.flush() | ||
| file2write.close() | ||
|
|
||
| print() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,63 +1,63 @@ | ||
| """Class to hold average and current values (such as loss values). | ||
| Typical usage example: | ||
| l = AverageMeter('autoencoder_loss') | ||
| l.update(2.33) | ||
| """ | ||
|
|
||
|
|
||
| class AverageMeter(object): | ||
| """Computes and stores the average and current value (such as loss values). | ||
| Attributes: | ||
| name: A string for the name for an instance of this object. | ||
| fmt: A string that acts as a formatting value during printing (ex. :f). | ||
| val: A float that is the most current value to be processed. | ||
| avg: A float average value calculated using the most recent sum and count values. | ||
| sum: A float running total that has been processed. | ||
| count: An integer count of the number of times that val has been updated. | ||
| """ | ||
|
|
||
| def __init__(self, name: str, fmt: str = ":f"): | ||
| """Initialization method. | ||
| Args: | ||
| name: The string name for an instance of this object. | ||
| fmt: A string formatting value during printing (ex. :f). | ||
| """ | ||
| self.name = name | ||
| self.fmt = fmt | ||
| self.reset() | ||
|
|
||
| def reset(self) -> None: | ||
| """Reset all numerical attributes in this object. | ||
| Modifies internal state of this object. | ||
| """ | ||
| self.val = 0 | ||
| self.avg = 0 | ||
| self.sum = 0 | ||
| self.count = 0 | ||
|
|
||
| def update(self, val: float, n: int = 1) -> None: | ||
| """Updates the numerical attributes in this object with the provided value and count. | ||
| Modifies internal state of this object. | ||
| Args: | ||
| val: A float value to be used to update the calculations. | ||
| n: A custom count value (default value is 1). | ||
| """ | ||
| self.val = val | ||
| self.sum += val * n | ||
| self.count += n | ||
| self.avg = self.sum / self.count | ||
|
|
||
| def __str__(self) -> str: | ||
| """Print a custom formatted string with the val and avg values. | ||
| Returns: | ||
| The custom format string. | ||
| """ | ||
| fmtstr = "{name} {val" + self.fmt + "} ({avg" + self.fmt + "})" | ||
| return fmtstr.format(**self.__dict__) | ||
| """Class to hold average and current values (such as loss values). | ||
| Typical usage example: | ||
| l = AverageMeter('autoencoder_loss') | ||
| l.update(2.33) | ||
| """ | ||
|
|
||
|
|
||
| class AverageMeter(object): | ||
| """Computes and stores the average and current value (such as loss values). | ||
| Attributes: | ||
| name: A string for the name for an instance of this object. | ||
| fmt: A string that acts as a formatting value during printing (ex. :f). | ||
| val: A float that is the most current value to be processed. | ||
| avg: A float average value calculated using the most recent sum and count values. | ||
| sum: A float running total that has been processed. | ||
| count: An integer count of the number of times that val has been updated. | ||
| """ | ||
|
|
||
| def __init__(self, name: str, fmt: str = ":f"): | ||
| """Initialization method. | ||
| Args: | ||
| name: The string name for an instance of this object. | ||
| fmt: A string formatting value during printing (ex. :f). | ||
| """ | ||
| self.name = name | ||
| self.fmt = fmt | ||
| self.reset() | ||
|
|
||
| def reset(self) -> None: | ||
| """Reset all numerical attributes in this object. | ||
| Modifies internal state of this object. | ||
| """ | ||
| self.val = 0 | ||
| self.avg = 0 | ||
| self.sum = 0 | ||
| self.count = 0 | ||
|
|
||
| def update(self, val: float, n: int = 1) -> None: | ||
| """Updates the numerical attributes in this object with the provided value and count. | ||
| Modifies internal state of this object. | ||
| Args: | ||
| val: A float value to be used to update the calculations. | ||
| n: A custom count value (default value is 1). | ||
| """ | ||
| self.val = val | ||
| self.sum += val * n | ||
| self.count += n | ||
| self.avg = self.sum / self.count | ||
|
|
||
| def __str__(self) -> str: | ||
| """Print a custom formatted string with the val and avg values. | ||
| Returns: | ||
| The custom format string. | ||
| """ | ||
| fmtstr = "{name} {val" + self.fmt + "} ({avg" + self.fmt + "})" | ||
| return fmtstr.format(**self.__dict__) |
Oops, something went wrong.