datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
multilingual-tts-benchmark
Multilingual Speech Benchmark for Zero-Shot TTS
A voice-cloning and intelligibility benchmark for 8 language subsets,
with 10,100 examples selected from Common Voice 17.0. Each example supplies
a speaker reference and an independently selected target text, with human
recordings as WER/CER and speaker-similarity anchors when the corresponding
audio is available. Corpus WER and the WavLM-FT evaluation follow
seed-tts-eval.
Version 3.1. Adds ru, kk through the same S1–S4 selection… See the full description on the dataset page: https://huggingface.co/datasets/nineninesix/multilingual-tts-benchmark.VoiceIsolation-Benchmark-Dataset
Voice Isolation Benchmark Dataset
265 real-world recordings for measuring how a second voice breaks speech-to-text, and how much Krisp Voice Isolation fixes it. Three scenarios, 47 speakers, real rooms, real headsets. No synthetic mixing.
265 recordings · 47 speakers · 3 scenarios · 65 scripts
Why this dataset exists
Modern STT engines handle noise well. They still fail when a second person talks near the microphone: they transcribe the wrong speaker, and voice… See the full description on the dataset page: https://huggingface.co/datasets/Krisp-AI/VoiceIsolation-Benchmark-Dataset.quranic-asr-benchmark
Quranic ASR Benchmark - leakage-free, held-out
A small, leakage-free benchmark (600 clips) for evaluating Arabic ASR on Quranic recitation
(Hafs riwayah). Every clip is verified absent from our training data, so it measures
generalization, not memorization. Same clips + same scoring for every model.
📊 Live leaderboard: https://huggingface.co/spaces/Muno459/quranic-asr-leaderboard
The set (600 clips, 200 per source)
Source
n
What it is
everyayah_heldout… See the full description on the dataset page: https://huggingface.co/datasets/Quran-Lab/quranic-asr-benchmark.persian-accents-benchmark
Persian Accents Benchmark
Dataset Summary
A benchmark for Persian automatic speech recognition (ASR): 279 short
utterances of informal Persian (Farsi) dialect speech across 16 regional accents,
released as a fixed evaluation set. Total audio duration is approximately 4.4
hours. The primary label is the transcription; each utterance also carries an
accent label (usable for accent classification as a secondary task) and an
emotion label as auxiliary metadata.
This… See the full description on the dataset page: https://huggingface.co/datasets/MR3z4/persian-accents-benchmark.quran-alignment-benchmark
Quran Recitation Alignment Benchmark
Audio recordings of Quran recitation with a reviewed word-level ground truth: every recited word, in the order it was recited, with its start and end time, plus the reviewed segmentation and non-Quran regions. This is the corpus behind the Quran Recitation Alignment Benchmark; the task, scoring rules, leaderboard and submission format are documented there, not here.
16 recordings · 357 minutes · 18,421 recited words · Hafs ʿan ʿĀṣim ·… See the full description on the dataset page: https://huggingface.co/datasets/QUD-Technologies/quran-alignment-benchmark.entity-transcription-benchmark
Entity Transcription Benchmark
Measures whether a speech recognition system transcribes named entities
correctly — as distinct from word error rate.
WER weights every token equally. The tokens that matter for redaction, lookup,
routing and search are proper nouns, and they are a small fraction of any
transcript. A system can improve WER while getting worse at exactly the words a
downstream consumer needs, and nothing in the standard evaluation will show it.
2,151 clips, 6.0… See the full description on the dataset page: https://huggingface.co/datasets/modulate/entity-transcription-benchmark.Agri_STT_Benchmarking_Dataset
Agri STT Benchmarking Dataset
10,808 farmer voice queries in Hindi, Telugu and Odia, with reference transcripts, for benchmarking automatic speech recognition in agricultural contexts. The audio is included in this repository.
Every recording is a smallholder farmer speaking a question to Farmer.Chat, an AI advisory service run by Digital Green. Reference transcripts were produced by human annotators. Nothing here is read from a script or recorded in a studio, so the audio… See the full description on the dataset page: https://huggingface.co/datasets/DigiGreen/Agri_STT_Benchmarking_Dataset.Vaani-Benchmark-V1.0
Vaani-Benchmark-V1.0
A curated Hindi ASR evaluation set collected as part of the Vaani project at IISc Bengaluru. This is a separate, held-out collection — distinct from the publicly released Vaani dataset — built specifically for benchmarking. This benchmark contains 5,050 audio segments from 1,103 speakers across 104 Indian districts, each with three independent human transcriptions.
Evaluation Toolkit
A standalone toolkit implementing this benchmark's scoring… See the full description on the dataset page: https://huggingface.co/datasets/ARTPARK-IISc/Vaani-Benchmark-V1.0.vocal-money-codeswitch-asr-benchmark
Vocal Money — Yoruba–English Code-Switched ASR Benchmark
A 210-clip evaluation subset used to benchmark five speech recognition systems on naturally
code-switched Yoruba–English speech, together with the reference transcriptions and the output of
every system on every clip, so that the published results can be recomputed or contradicted.
Produced for the MLC (Africa) × Intron Agentic Voice AI Challenge, Deep Learning Indaba 2026.
Team Vocal Money — Hospice Hounfodji, Mohamed… See the full description on the dataset page: https://huggingface.co/datasets/Kimyayd/vocal-money-codeswitch-asr-benchmark.clipquill-asr-benchmark
Measuring whisper-tiny vs whisper-base in a browser tab
Word error rate, wall-clock timing, transfer size and peak memory for two
quantised Whisper tiers running entirely client-side in a real Chrome window,
with the scripts that produced every number.
If you are building an in-browser transcription page, the two results worth
knowing before you pick a model tier:
On clean synthetic audio the two tiers tie. If that is all you test, you
will conclude the tier does not matter… See the full description on the dataset page: https://huggingface.co/datasets/sophia8888/clipquill-asr-benchmark.humans-benchmark
HUMANS Benchmark Dataset
Authors: Woody Haosheng Gan¹, William Held²'³, Diyi Yang²
¹University of Southern California, ²Stanford University, ³OpenAthena
This dataset is part of the Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment paper.
HUMANS (HUman-aligned Minimal Audio evaluatioN Subsets for Large Audio Models) Benchmark is designed to efficiently evaluate Large Audio Models using minimal subsets while predicting human preferences through learned… See the full description on the dataset page: https://huggingface.co/datasets/woodygan/humans-benchmark.Persian-ASR-BenchmarkThis dataset consists of 3 hours of 16kHz audio collected from diverse environments to better represent real-world scenarios. The recordings were sourced from audiobooks, YouTube, and other public sources, ensuring a wide variety of speech styles and acoustic conditions.
One key advantage of this dataset is that it was collected from recent sources within the last few months, ensuring no overlap with training data and fairness for evaluating other STT models.
To enable a robust and fair… See the full description on the dataset page: https://huggingface.co/datasets/C1Tech/Persian-ASR-Benchmark.intron-stt_tts-benchmark
Code-switched benchmark audio
The exact 16 recordings used to benchmark speech models for the Sahara
CodeSwitch Africa Challenge. Published so the reported numbers can be checked
against the audio that produced them.
Every clip is intra-sentential code-switching — one speaker moving between a
Nigerian language and English inside a single utterance, which is the case the
challenge is judged on.
Language
Clips
Hausa
4
Igbo
4
Nigerian Pidgin
4
Yoruba
4… See the full description on the dataset page: https://huggingface.co/datasets/yusasif/intron-stt_tts-benchmark.asr-benchmark-outputs
SaarAI ASR Benchmark Outputs
Raw per-utterance model outputs (transcription manifests) produced by the gsma-asr-bench runners on SaarAI/asr-leaderboard-datasets.
files: 570
utterances: 4615160
languages: 7
models: 50
Layout
data/<language_name>/<split>__<dataset_config>__<model_slug>.jsonl
index.jsonl # one record per file (language, split, model, rows, sha256, ...)
index.csv
Directories categorise by language name; the file name begins with the split name… See the full description on the dataset page: https://huggingface.co/datasets/SaarAI/asr-benchmark-outputs.Fasih-TTS-Benchmark
Fasih-TTS-Benchmark
Evaluation audio and objective scores for the
Fasih-TTS-V1 Arabic (MSA / Fusha)
text-to-speech model. Every clip is the model's own output, paired with its reference text, its
Whisper-large-v3 transcription, and per-clip WER / CER.
Contents
Split (test_set)
Clips
Purpose
Mean CER
silma_msa
10
SILMA open-source Arabic TTS benchmark (MSA sentences)
2.0%
samples
3
General showcase (greeting, fiqh, reflection)
0.6%
consistency
8… See the full description on the dataset page: https://huggingface.co/datasets/NightPrince/Fasih-TTS-Benchmark.a5sv2-asr-benchmark-dataset
A5Sv2 ASR Benchmark Dataset
Public references, saved predictions, scores, and provenance for the
A5Sv2 ASR benchmark. The benchmark evaluates
streaming English ASR on four fixed public corpora with approximately equal normalized reference
word counts.
Corpus
Fixed selection
Reference words
Audio in this repository
Mega-ASR / Voices-in-the-Wild-2M
1,250 utterances, 250 per acoustic condition
32,928
Yes
AMI
7 scenario-only unseen-evaluation meetings
32,928
Yes
DiPCo… See the full description on the dataset page: https://huggingface.co/datasets/AirCaps/a5sv2-asr-benchmark-dataset.gametime
Gametime Benchmark
The Gametime dataset provides lightweight, streaming-friendly splits for TTS/ASR/SpokenLM prototyping.For full details, please refer to the paper:👉 Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
📦 Download Options
1️⃣ Recommended — Full ZIP Download
If you prefer the original folder layout you can download one of the ZIPs packaged in gametime/download/. There are two kinds available in this repository:… See the full description on the dataset page: https://huggingface.co/datasets/gametime-benchmark/gametime.script-fidelity-benchmark
Script fidelity benchmark
Anonymous supplement for the paper "Script collapse in multilingual ASR:
A reference-free metric and 100-pair benchmark."
Script Fidelity Rate (SFR) measures the fraction of ASR hypothesis characters
that belong to the expected target script. WER measures word edits, while SFR
checks whether the output is written in the target orthography.
Related resources:
PyPI package: https://pypi.org/project/script-fidelity/
Hugging Face Evaluate metric:… See the full description on the dataset page: https://huggingface.co/datasets/themechanism/script-fidelity-benchmark.ASR-Benchmark-Public
Revolab ASR Benchmark (Public Split)
The Revolab ASR Benchmark is a human-annotated evaluation dataset for Malaysian Malay speech recognition. This is the public split - a downloadable subset that anyone can use to run their own evaluation. A larger private split is used to maintain the official leaderboard.
Dataset Details
Audio samples: 820
Duration: ~2.2 hours
Languages: Bahasa Malaysia and English (including code-switching)
Sample rate: 16kHz
License:… See the full description on the dataset page: https://huggingface.co/datasets/Revolab/ASR-Benchmark-Public.nepali-homophone-asr-benchmark
Nepali Confusable-Pair Voice Dataset
A small research dataset for studying Nepali speech-to-text (ASR) errors on context-dependent confusable / homophonic words.
Dataset size
54 total WAV recordings preserved
50 recordings provisionally mapped to canonical sentence prompts
3 valid speech recordings intentionally left without a transcript because their exact prompt is unresolved
1 intentional near-silent recording retained as a no-speech / hallucination challenge… See the full description on the dataset page: https://huggingface.co/datasets/Fat-Shork/nepali-homophone-asr-benchmark.kurdish-multidialect-asr-benchmark
Kurdish Dialect Speech Corpus
This project aims to provide a multi-dialect speech recognition benchmark for the Kurdish language. The Central Kurdish portion is the same as the Asosoft benchmark. The sentences were originally written in Central Kurdish (CKB), translated into other Kurdish dialects, and then recorded by native speakers.
The current version includes three Kurdish dialects: Central Kurdish, Northern Kurdish, and Southern Kurdish. A Hawrami version and the Badini… See the full description on the dataset page: https://huggingface.co/datasets/aranemini/kurdish-multidialect-asr-benchmark.ASR-Benchmarking-Dataset
Hindi STT Benchmarking Eval
Overview
This dataset packages the Hindi eval split used for STT benchmarking across six Vistaar-derived parts: IndicTTS, FLEURS, CommonVoice, Kathbath, Kathbath noisy, and MUCS. Each row contains the audio, original reference transcript, and raw plus normalized transcripts from Ringg, ElevenLabs, Deepgram, and Sarvam.
The dataset contains 10,000 utterances and about 15.5 hours of 16 kHz mono WAV audio.
The dataset is published as part-specific… See the full description on the dataset page: https://huggingface.co/datasets/RinggAI/ASR-Benchmarking-Dataset.darija-asr-benchmark-6speaker
Darija ASR 6-Speaker Benchmark
A fixed, paired 20-utterance benchmark read identically by 6 held-out speakers (3
female: F1, F2, F3; 3 male: M1, M2, M3 -- none present in any training corpus),
used to evaluate cross-speaker generalization for a Moroccan Darija (Arabizi)
Whisper fine-tuning pipeline (paper not yet published -- citation forthcoming).
Consent and anonymization
Written informed consent was obtained from all six speakers for the recording and… See the full description on the dataset page: https://huggingface.co/datasets/zadterishi/darija-asr-benchmark-6speaker.darija-asr-benchmark-6speaker
Darija ASR 6-Speaker Benchmark
A fixed, paired 20-utterance benchmark read identically by 6 held-out speakers (3
female: F1, F2, F3; 3 male: M1, M2, M3 -- none present in any training corpus),
used to evaluate cross-speaker generalization for a Moroccan Darija (Arabizi)
Whisper fine-tuning pipeline (paper not yet published -- citation forthcoming).
Consent and anonymization
Written informed consent was obtained from all six speakers for the recording and… See the full description on the dataset page: https://huggingface.co/datasets/abnajlae/darija-asr-benchmark-6speaker.French-Medical-Transcription-Benchmark
🩺 French Medical Transcription Evaluation Dataset
Ce dataset a été créé et ouvert à la communauté dans le cadre du développement R&D de LucioleScribe, la plateforme souveraine de transcription IA 100% locale, spécifiquement conçue pour les milieux médicaux et juridiques (compatibilité RGPD, HDS, et architectures Air-Gapped).
🔗 Découvrir LucioleScribe Édition Santé | ⚙️ Voir le Pipeline Technologique Local
📊 Présentation du Dataset
L'évaluation des modèles de… See the full description on the dataset page: https://huggingface.co/datasets/AWANNABY/French-Medical-Transcription-Benchmark.visualears-benchmark-269-gold
🗂️ visualears-benchmark-269-gold
English + فارسی · Part of Shenava 1.0 · Project hub · SLT paper submission
🌟 At a glance | معرفی سریع
English
فارسی
🎯 Purpose
269-record gold/noisy benchmark dataset.
معیار طلایی ۲۶۹ نمونهای برای بررسی سریع خطاهای گفتار نویزی و مقایسهٔ نسخههای مدل.
🧩 Role
evaluation and benchmarking asset
مصنوع ارزیابی و بنچمارک
📦 Snapshot
276 files; approximately 44.35 MB
276 فایل؛ حدود 44.35 MB
🧱 Packaging
1 Parquet… See the full description on the dataset page: https://huggingface.co/datasets/Reza2kn/visualears-benchmark-269-gold.bam-asr-benchmark
Bambara ASR Benchmark
The first standardized evaluation set for Automatic Speech Recognition in Bambara (Bamanankan). One hour of studio-quality constitutional text, transcribed and validated by linguists from Mali's Direction Nationale de l'Éducation Non Formelle et des Langues Nationales (DNENF-LN).
This benchmark accompanies the paper "Where Are We at with Automatic Speech Recognition for the Bambara Language?" and the public leaderboard at MALIBA-AI/bambara-asr-leaderboard.… See the full description on the dataset page: https://huggingface.co/datasets/sudoping01/bam-asr-benchmark.conversational-streaming-asr-benchmark
SquadStack Conversational Streaming ASR Benchmark (8 kHz)
Version 1.0.0 · maintained by SquadStack
Schema · Leaderboard · Latency · Submit a system · Licence · Terms of use
Key takeaways
What this is. 863 real Hindi–English telesales calls (5.53 hours of customer speech, 8 kHz phone audio), human-transcribed turn by turn, and 11 speech recognisers scored on them. The question it answers: which recogniser should run inside an Indian voice agent, judged on… See the full description on the dataset page: https://huggingface.co/datasets/Squadstack/conversational-streaming-asr-benchmark.nepali-asr-benchmark
Nepali ASR Benchmark
Per-utterance reference, hypothesis, WER, and CER for the six released Nepali ASR
checkpoints evaluated on three independent test sets. Released alongside the paper
Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech
Recognition.
Contents
Field
Type
Description
utterance_id
string
stable identifier {test_set}-{index}
reference
string
NFC-normalised gold transcription (Devanagari)
hypothesis
string… See the full description on the dataset page: https://huggingface.co/datasets/sumanpaudel1997/nepali-asr-benchmark.humans-benchmark
HUMANS Benchmark Dataset (Anonymous, Under Review)
This dataset is part of the HUMANS (HUman-aligned Minimal Audio evaluatioN Subsets for Large Audio Models) Benchmark, designed to efficiently evaluate Large Audio Models using minimal subsets while predicting human preferences through learned regression weights.
Installation
Install the HUMANS evaluation package from GitHub (our anonymous repo):
# Option 1: Install via pip
pip install… See the full description on the dataset page: https://huggingface.co/datasets/HUMANSBenchmark/humans-benchmark.