selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-20 20:29:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #13 from Monadical-SAS/whisper-jax-gokul

Browse Source 
update
This commit is contained in:
projects-g
2023-06-14 23:33:18 +05:30
committed by GitHub
parent 9269a519bd 9d2d6dd7e4
commit 6c7c09d92e
3 changed files with 28 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
.DS_Store vendored Normal file
View File

Binary file not shown.

3
config.ini
View File

@@ -7,5 +7,4 @@ OPENAI_APIKEY=
WHISPER_MODEL_SIZE=tiny
AWS_ACCESS_KEY=***REMOVED***
AWS_SECRET_KEY=***REMOVED***
BUCKET_NAME='reflector-bucket'
BUCKET_NAME='reflector-bucket'

54
whisjax.py
View File

@@ -223,32 +223,32 @@ def create_talk_diff_scatter_viz():
# to load, my_mappings = pickle.load( open ("mappings.pkl", "rb") )
# pick the 2 most matched topic to be used for plotting
topic_times = collections.defaultdict(int)
for key in ts_to_topic_mapping_top_1.keys():
duration = key[1] - key[0]
topic_times[ts_to_topic_mapping_top_1[key]] += duration
topic_times = sorted(topic_times.items(), key=lambda x: x[1], reverse=True)
cat_1 = topic_times[0][0]
cat_1_name = topic_times[0][0]
cat_2_name = topic_times[1][0]
# Scatter plot of topics
df = df.assign(parse=lambda df: df.text.apply(st.whitespace_nlp_with_sentences))
corpus = st.CorpusFromParsedDocuments(
df, category_col='ts_to_topic_mapping_top_1', parsed_col='parse'
).build().get_unigram_corpus().compact(st.AssociationCompactor(2000))
html = st.produce_scattertext_explorer(
corpus,
category=cat_1,
category_name=cat_1_name,
not_category_name=cat_2_name,
minimum_term_frequency=0, pmi_threshold_coefficient=0,
width_in_pixels=1000,
transform=st.Scalers.dense_rank
)
open('./demo_compact.html', 'w').write(html)
# topic_times = collections.defaultdict(int)
# for key in ts_to_topic_mapping_top_1.keys():
# duration = key[1] - key[0]
# topic_times[ts_to_topic_mapping_top_1[key]] += duration
#
# topic_times = sorted(topic_times.items(), key=lambda x: x[1], reverse=True)
#
# cat_1 = topic_times[0][0]
# cat_1_name = topic_times[0][0]
# cat_2_name = topic_times[1][0]
#
# # Scatter plot of topics
# df = df.assign(parse=lambda df: df.text.apply(st.whitespace_nlp_with_sentences))
# corpus = st.CorpusFromParsedDocuments(
# df, category_col='ts_to_topic_mapping_top_1', parsed_col='parse'
# ).build().get_unigram_corpus().compact(st.AssociationCompactor(2000))
# html = st.produce_scattertext_explorer(
# corpus,
# category=cat_1,
# category_name=cat_1_name,
# not_category_name=cat_2_name,
# minimum_term_frequency=0, pmi_threshold_coefficient=0,
# width_in_pixels=1000,
# transform=st.Scalers.dense_rank
# )
# open('./demo_compact.html', 'w').write(html)
def main():
@@ -333,7 +333,7 @@ def main():
# S3 : Push artefacts to S3 bucket
files_to_upload = ["transcript.txt", "transcript_timestamps.txt",
"demo_compact.html", "df.pkl",
"df.pkl",
"wordcloud.png", "mappings.pkl"]
upload_files(files_to_upload)