Fisher English

by LDC

2000h of telephone conversations — scaled-up successor to Switchboard.

Looking at Fisher English? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for conversational English ASR training at scale. Pricing: paid.

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

What it is

Fisher English Parts 1+2 (LDC2004S13/LDC2005S13) is ~2000 hours of US English conversational telephone speech — the standard high-quantity conversational-ASR corpus. LDC paid.

Best for: Conversational English ASR training at scale.
Watch out for: LDC license · paid · 8 kHz telephone speech. Cite: Cieri et al., LREC 2004.

Install / use

Go to Fisher English catalog.ldc.upenn.edu

Features

Speaker diarizationYes
Word-level timestampsNo
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

Fisher English vs Whipscribe

FeatureFisher EnglishWhipscribe
CategoryOpen sourceTranscription APIs
Pricingpaid$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationYesYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsLDCWeb, API, MCP

Alternatives to Fisher English

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.