📊
Whisper Small Shona dataset by steja
⭐ 26.7
📊
Dataset

Whisper Small Shona

by steja hf-model--steja--whisper-small-shona
Nexus Index
26.7 Top 100%
S: Semantic 50
A: Authority 0
P: Popularity 0
R: Recency 100
Q: Quality 38
Tech Context
Vital Performance
0 DL / 30D
0.0%
Data Integrity 26.7 FNI Score
- Size
- Rows
Parquet Format
- Tokens
Dataset Information Summary
Entity Passport
Registry ID hf-model--steja--whisper-small-shona
Provider huggingface
📜

Cite this dataset

Academic & Research Attribution

BibTeX 
@misc{hf_model__steja__whisper_small_shona,
  author = {steja},
  title = {Whisper Small Shona Dataset},
  year = {2026},
  howpublished = {\url{https://free2aitools.com/dataset/hf-model--steja--whisper-small-shona}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
steja. (2026). Whisper Small Shona [Dataset]. Free2AITools. https://free2aitools.com/dataset/hf-model--steja--whisper-small-shona

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

⚖ī¸ Nexus Index V2.0

Methodology Index Protocol
26.7
TOP 100% SYSTEM IMPACT
Semantic (S) 50
Authority (A) 0
Popularity (P) 0
Recency (R) 100
Quality (Q) 38

đŸ’Ŧ Index Insight

FNI V2.0 for Whisper Small Shona: Semantic (S:50), Authority (A:0), Popularity (P:0), Recency (R:100), Quality (Q:38).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit
Unbiased Data Node Refresh: VFS Live

👁ī¸ Data Preview

📊

Row-level preview not available for this dataset.

Schema structure is shown in the Field Logic panel when available.

đŸ§Ŧ Field Logic

đŸ§Ŧ

Schema not yet indexed for this dataset.

Dataset Specification

Whisper small shona

This model is a fine-tuned version of openai/whisper-small on the google/fleurs sn_zw dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1220
  • Wer: 49.9096

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 3
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 48
  • total_eval_batch_size: 48
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0064 24.24 400 0.9630 50.7233
0.001 48.48 800 1.0617 49.9397
0.0005 72.73 1200 1.1016 49.9397
0.0004 96.97 1600 1.1220 49.9096
0.0003 121.21 2000 1.1298 50.0422

Framework versions

  • Transformers 4.37.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.16.1
  • Tokenizers 0.15.1
🤗 Data Source: Hugging Face ↗
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹī¸ Verify with original source

🛡ī¸ Dataset Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-model--steja--whisper-small-shona
slug
steja--whisper-small-shona
source
huggingface
author
steja
license
tags

⚙ī¸ Technical Specs

architecture
null
params billions
null
context length
null
pipeline tag

📊 Engagement & Metrics

downloads
0
stars
0
forks
0

Data indexed from public sources. Updated daily.