|
Welcome to the DrivenData community forum
|
|
1
|
5500
|
April 27, 2021
|
|
Poverty Prediction Results Page is Up
|
|
0
|
5
|
April 10, 2026
|
|
Now that we are done, who wants to talk about what worked?
|
|
9
|
136
|
April 9, 2026
|
|
Submissions closed?
|
|
1
|
70
|
April 8, 2026
|
|
Training data - incredibly corrupt
|
|
1
|
73
|
April 7, 2026
|
|
Smoke Test Execution Time Limit?
|
|
0
|
5
|
April 6, 2026
|
|
Urgent: how many submission time left?
|
|
8
|
156
|
April 4, 2026
|
|
Public vs Private LB %
|
|
5
|
284
|
April 2, 2026
|
|
Can I expect only these phonetic characters or more?
|
|
6
|
174
|
March 31, 2026
|
|
Extremely long wait times because of Queues
|
|
16
|
254
|
March 31, 2026
|
|
Whisper Licensing Terms
|
|
1
|
90
|
March 27, 2026
|
|
Clarification on rules
|
|
3
|
100
|
March 26, 2026
|
|
Uploading of Submission taking a long time
|
|
1
|
67
|
March 25, 2026
|
|
Looking for a team mate (team leader/captain) from USA
|
|
1
|
61
|
March 24, 2026
|
|
Use of Adult Speech Data for Pretraining and Fine-Tuning
|
|
3
|
162
|
March 23, 2026
|
|
Can we use data from other track?
|
|
7
|
173
|
March 18, 2026
|
|
Poverty Prediction Challenge Winning Solutions
|
|
0
|
62
|
March 16, 2026
|
|
Me Ranting over this Competition
|
|
6
|
281
|
March 16, 2026
|
|
Error running benchmark code:
|
|
3
|
33
|
March 16, 2026
|
|
Pass smoke test but fail normal submission
|
|
7
|
297
|
March 16, 2026
|
|
Submission pass smoke test but fail normal submission
|
|
2
|
93
|
March 14, 2026
|
|
Entire Smoketest Used For Scoring?
|
|
1
|
77
|
March 14, 2026
|
|
vLLM + CUDA mismatch
|
|
7
|
266
|
March 13, 2026
|
|
Question about Smoke Test Dataset and WER Calculation
|
|
4
|
137
|
March 12, 2026
|
|
Runtime Package Request: fairseq2
|
|
1
|
61
|
March 12, 2026
|
|
New Tutorial: Finetuning Wav2Vec2 with Hugging Face Transformers for the Phonetic Track
|
|
0
|
108
|
March 11, 2026
|
|
Cannot find the "SnomedCT_InternationalRF2_PRODUCTION_20230531T120000Z_Challenge_Edition"
|
|
1
|
18
|
March 11, 2026
|
|
Smoke test utterances
|
|
3
|
100
|
March 7, 2026
|
|
import librosa import librosa.display import numpy as np import matplotlib.pyplot as plt def process_child_speech(file_path): # 1. Load the audio file # We use sr=16000 because most speech models expect 16kHz audio, sample_rate = librosa.load
|
|
0
|
5
|
March 6, 2026
|
|
Will the phonetic audio be no more than 60 seconds long on the test?
|
|
3
|
120
|
March 4, 2026
|