CallHome English

by LDC

60h of unscripted home-telephone conversations — diarization + ASR benchmark.

TL;DR

60h of unscripted home-telephone conversations — diarization + ASR benchmark.

Best for conversational diarization + ASR with informal-register telephone speech. Pricing: paid.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
paid
Platforms
LDC

What it is

The CallHome series is 30-minute spontaneous calls between family/friends across 6 languages. Standard conversational-diarization benchmark. LDC paid.

Best for: Conversational diarization + ASR with informal-register telephone speech.
Watch out for: LDC license · paid · CallHome ships in English / Mandarin / Spanish / Japanese / German / Arabic. Cite: Canavan et al., 1997.

Install / use

https://catalog.ldc.upenn.edu/LDC97S42  # LDC membership

Features

Speaker diarizationYes
Word-level timestampsNo
Streaming / real-timeNo
Languages supported6
HIPAA eligibleNo

CallHome English vs Whipscribe

FeatureCallHome EnglishWhipscribe
CategoryOpen sourceTranscription APIs
Pricingpaidfree beta
Speaker diarizationYesYes
Word timestampsNoYes
StreamingNoNo
Languages699
PlatformsLDCWeb, API, MCP

Alternatives to CallHome English

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.