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
from pydub import AudioSegment, silence | |
import pandas as pd | |
def build_segments(audio, length_segment=10, dbfs=0): | |
silences = silence.detect_silence(audio, min_silence_len=1000, silence_thresh=dbfs-16) | |
dfp_silences = pd.DataFrame(silences, columns = ["start_timecode", "end_timecode"]) | |
threshold_segment = int(length_segment * 60 * 1000) | |
first_timecode = 0 | |
last_timecode = int(audio.duration_seconds * 1000) |
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
from pathlib import Path | |
from openai import OpenAI | |
client_openai = OpenAI( | |
# This is the default and can be omitted | |
api_key="sk-XXX", | |
) | |
def get_transcript_openai_api(file, language="fr"): | |
# f = open(file, "rb") |
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
import torch | |
from transformers import pipeline | |
device = "cuda:0" if torch.cuda.is_available() else "cpu" | |
mapping = {"whisper-tiny" : "tiny", "whisper-small" : "small", "whisper-medium" : "medium", "whisper-base" : "base"} | |
hf_model_name = "whisper-medium" | |
size_model = mapping[hf_model_name] #tiny, base, small, medium | |
model = pipeline( |
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
import whisper | |
size_model = "medium" #the type of model in the model card , with .en or not | |
model = whisper.load_model(size_model, device="cuda") | |
def get_transcript_local_whisper(model, file, language): | |
audio = whisper.load_audio(file) | |
audio = whisper.pad_or_trim(audio) | |
mel = whisper.log_mel_spectrogram(audio).to(model.device) | |
result = whisper.decode(model, mel, language=language) |
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
from time import time | |
from hyperopt import fmin, tpe, hp, anneal, Trials | |
import mlflow | |
from sklearn.metrics import mean_squared_error | |
import surprise | |
def evaluate_model(model, dfp_ratings_test): | |
dfp_evaluation = dfp_ratings_test.copy() | |
dfp_evaluation["rating_predicted"] = dfp_evaluation.apply(lambda row: compute_ranking(model, str(row["userid"]), str(row["contentid"])), axis=1) | |
return mean_squared_error(dfp_evaluation["rating"].tolist(), dfp_evaluation["rating_predicted"].tolist(), squared=False) |
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
for idx, row in dfp_archetypes.iterrows(): | |
print("ARCHETYPE:", row["userid"]) | |
inventory_positive = dfp_inventory_positive.loc[row["userid"]] | |
# Get the candidates | |
buffer = [] | |
for contentid in inventory_positive: | |
closest_contentids = get_closest_neighbors(model_retriever_items, contentid, 10, type_="item") | |
buffer.extend(closest_contentids) | |
sp_count_contentids = pd.Series(dict(Counter(buffer))).sort_values(ascending=False) |
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
def get_closest_neighbors(model, entityid, k, type_="item"): | |
if type_ == "item": | |
inner_entity_id = model.trainset.to_inner_iid(entityid) | |
else: | |
inner_entity_id = model.trainset.to_inner_uid(entityid) | |
closest_entity_id = model.get_neighbors(inner_entity_id, k) | |
if type_ == "item": | |
return [model.trainset.to_raw_iid(id_) for id_ in closest_entity_id] |
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
def build_recommendations(model, userid, inventory, dfp_items, k=5): | |
dfp_recommendations = dfp_items[["title", "category", "year", "contentid"]] | |
dfp_recommendations["contentid"] = dfp_recommendations["contentid"].astype(str) | |
dfp_recommendations["rating_predicted"] = dfp_recommendations["contentid"].apply(lambda contentid: compute_ranking(model, str(userid), str(contentid))) | |
dfp_recommendations.sort_values("rating_predicted", ascending=False, inplace=True) | |
dfp_recommendations = dfp_recommendations.loc[dfp_recommendations["contentid"].isin(inventory) == False] | |
return dfp_recommendations.head(k).reset_index(drop=True) |
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
import pandas as pd | |
from kats import models | |
# Selection your base model | |
def build_model(model, kts): | |
if model == "prophet": | |
return models.prophet.ProphetModel(kts, params=models.prophet.ProphetParams()) | |
elif model == "theta": | |
return models.theta.ThetaModel(kts, params=models.theta.ThetaParams()) | |
elif model == "holtwinters": |
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
from kats.consts import TimeSeriesData | |
def build_kats_timeserie(dfp, column_time = "time", column_value = "value"): | |
return TimeSeriesData(time=dfp[column_time], value=dfp[column_value]) | |
kts_test = build_kats_timeserie(dfp_test,"date","value") |
NewerOlder