chore(transcription): add proper english video fixture

larriereguichet · May 15, 2024 · 70f68b9 · 70f68b9
1 parent dd3c112
commit 70f68b9
Show file tree

Hide file tree

Showing 7 changed files with 69 additions and 42 deletions.
diff --git a/packages/tests/fixtures/transcription/README.md b/packages/tests/fixtures/transcription/README.md
diff --git a/packages/tests/fixtures/transcription/videos/README.md b/packages/tests/fixtures/transcription/videos/README.md
@@ -0,0 +1,16 @@
+🇫🇷 DRANE Occitanie - Communiquer lors d'une classe transplantée
+[./communiquer-lors-dune-classe-transplantee.mp4](communiquer-lors-dune-classe-transplantee.mp4)
+> https://podeduc.apps.education.fr/numerique-educatif/video/21893-communiquer-lors-dune-classe-transplantee/
+>
+> CC BY-NC-SA 4.0 Deed
+> Attribution-NonCommercial-ShareAlike 4.0 International
+
+🇫🇷 [Accompagner la victime d'une dérive sectaire ou d'une emprise mentale](https://www.fun-mooc.fr/fr/cours/accompagner-la-victime-de-derive-sectaire/)
+> Centre Contre les Manipulations Mentales (CCMM)
+> [CC BY-NC-ND 4.0 Deed](https://creativecommons.org/licenses/by-nc-nd/4.0/)
+> Attribution-NonCommercial-NoDerivs 4.0 International
+
+🇺🇸 [The Last Man On Earth (1964)](https://archive.org/details/TheLastManOnEarthHD)
+> PDM 1.0 Deed
+> Public Domain Mark 1.0 Universal
+> https://creativecommons.org/publicdomain/mark/1.0/
diff --git a/packages/tests/fixtures/transcription/videos/the_last_man_on_earth.mp4 b/packages/tests/fixtures/transcription/videos/the_last_man_on_earth.mp4
diff --git a/packages/tests/fixtures/transcription/videos/the_last_man_on_earth.txt b/packages/tests/fixtures/transcription/videos/the_last_man_on_earth.txt
@@ -0,0 +1,5 @@
+December, 1965.
+Is that all it has been since
+I inherited the world?
+Only three years.
+It seems like a hundred million.
diff --git a/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts b/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts
@@ -1,4 +1,4 @@
-/* eslint-disable @typescript-eslint/no-unused-expressions */
+/* eslint-disable @typescript-eslint/no-unused-expressions, max-len */
 import { expect, config } from 'chai'
 import { createLogger } from 'winston'
 import { join } from 'path'
@@ -16,7 +16,7 @@ config.truncateThreshold = 0
 
 describe('Open AI Whisper transcriber', function () {
   const transcriptDirectory = join(root(), 'test-transcript')
-  const shortVideoPath = buildAbsoluteFixturePath('video_short.mp4')
+  const shortVideoPath = buildAbsoluteFixturePath('transcription/videos/the_last_man_on_earth.mp4')
   const frVideoPath = buildAbsoluteFixturePath('transcription/videos/derive_sectaire.mp4')
   const referenceTranscriptFile = new TranscriptFile({
     path: buildAbsoluteFixturePath('transcription/videos/derive_sectaire.txt'),
@@ -43,16 +43,16 @@ describe('Open AI Whisper transcriber', function () {
   it('Should transcribe a media file and provide a valid path to a transcript file in `vtt` format by default', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.vtt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.vtt'),
       language: 'en',
       format: 'vtt'
     }))).to.be.true
 
     expect(await transcript.read()).to.equals(
       `WEBVTT
 
-00:00.000 --> 00:02.000
-You
+00:00.000 --> 00:13.000
+December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 
 `
     )
@@ -61,15 +61,15 @@ You
   it('May produce a transcript file in the `srt` format', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.srt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.srt'),
       language: 'en',
       format: 'srt'
     }))).to.be.true
 
     expect(await transcript.read()).to.equal(
       `1
-00:00:00,000 --> 00:00:02,000
-You
+00:00:00,000 --> 00:00:13,000
+December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 
 `
     )
@@ -78,13 +78,14 @@ You
   it('May produce a transcript file in the `txt` format', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.txt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.txt'),
       language: 'en',
       format: 'txt'
     }))).to.be.true
 
-    expect(await transcript.read()).to.equal(`You
-`)
+    expect(await transcript.read()).to.equal(`December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
+`
+    )
   })
 
   it('May transcribe a media file using a local PyTorch model', async function () {

diff --git a/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts b/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts
@@ -18,13 +18,8 @@ config.truncateThreshold = 0
 
 describe('Linto timestamped Whisper transcriber', function () {
   const transcriptDirectory = join(root(), 'test-transcript')
-  const shortVideoPath = buildAbsoluteFixturePath('video_short.mp4')
+  const shortVideoPath = buildAbsoluteFixturePath('transcription/videos/the_last_man_on_earth.mp4')
   const frVideoPath = buildAbsoluteFixturePath('transcription/videos/derive_sectaire.mp4')
-  const referenceTranscriptFile = new TranscriptFile({
-    path: buildAbsoluteFixturePath('transcription/videos/derive_sectaire.txt'),
-    language: 'fr',
-    format: 'txt'
-  })
   const transcriber = new WhisperTimestampedTranscriber(
     {
       name: 'whisper-timestamped',
@@ -45,16 +40,22 @@ describe('Linto timestamped Whisper transcriber', function () {
   it('Should transcribe a media file and produce a transcript file in `vtt` with a ms precision', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.vtt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.vtt'),
       language: 'en',
       format: 'vtt'
     }))).to.be.true
 
     expect(await transcript.read()).to.equals(
       `WEBVTT
 
-00:02.480 --> 00:02.500
-you
+00:00.460 --> 00:02.080
+December 1965.
+
+00:03.700 --> 00:08.800
+Is that all it has been since I inherited the world only three years?
+
+00:10.420 --> 00:11.900
+Seems like a hundred million.
 
 `
     )
@@ -63,15 +64,23 @@ you
   it('May produce a transcript file in the `srt` format with a ms precision', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.srt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.srt'),
       language: 'en',
       format: 'srt'
     }))).to.be.true
 
     expect(await transcript.read()).to.equals(
       `1
-00:00:02,480 --> 00:00:02,500
-you
+00:00:00,460 --> 00:00:02,080
+December 1965.
+
+2
+00:00:03,700 --> 00:00:08,800
+Is that all it has been since I inherited the world only three years?
+
+3
+00:00:10,420 --> 00:00:11,900
+Seems like a hundred million.
 
 `
     )
@@ -80,12 +89,14 @@ you
   it('May produce a transcript file in `txt` format', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.txt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.txt'),
       language: 'en',
       format: 'txt'
     }))).to.be.true
 
-    expect(await transcript.read()).to.equals(`you
+    expect(await transcript.read()).to.equals(`December 1965.
+Is that all it has been since I inherited the world only three years?
+Seems like a hundred million.
 `)
   })
 

diff --git a/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts b/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts
@@ -16,7 +16,7 @@ config.truncateThreshold = 0
 
 describe('Whisper CTranslate2 transcriber', function () {
   const transcriptDirectory = join(root(), 'test-transcript')
-  const shortVideoPath = buildAbsoluteFixturePath('video_short.mp4')
+  const shortVideoPath = buildAbsoluteFixturePath('transcription/videos/the_last_man_on_earth.mp4')
   const frVideoPath = buildAbsoluteFixturePath('transcription/videos/derive_sectaire.mp4')
   const transcriber = new Ctranslate2Transcriber(
     {
@@ -37,12 +37,12 @@ describe('Whisper CTranslate2 transcriber', function () {
 
   it('Should transcribe a media file and provide a valid path to a transcript file in `vtt` format by default', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
-    expect(await transcript.equals(new TranscriptFile({ path: join(transcriptDirectory, 'video_short.vtt'), language: 'en' }))).to.be.true
+    expect(await transcript.equals(new TranscriptFile({ path: join(transcriptDirectory, 'the_last_man_on_earth.vtt'), language: 'en' }))).to.be.true
     expect(await readFile(transcript.path, 'utf8')).to.equal(
       `WEBVTT
 
-00:00.000 --> 00:02.000
-You
+00:00.000 --> 00:12.000
+December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 
 `
     )
@@ -51,15 +51,15 @@ You
   it('May produce a transcript file in the `srt` format', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.srt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.srt'),
       format: 'srt',
       language: 'en'
     }))).to.be.true
 
     expect(await readFile(transcript.path, 'utf8')).to.equal(
       `1
-00:00:00,000 --> 00:00:02,000
-You
+00:00:00,000 --> 00:00:12,000
+December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 
 `
     )
@@ -68,12 +68,12 @@ You
   it('May produce a transcript file in the `txt` format', async function () {
     const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.txt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.txt'),
       format: 'txt',
       language: 'en'
     }))).to.be.true
 
-    expect(await transcript.read()).to.equal(`You
+    expect(await transcript.read()).to.equal(`December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 `)
   })
 
@@ -86,12 +86,12 @@ You
       format: 'txt'
     })
     expect(await transcript.equals(new TranscriptFile({
-      path: join(transcriptDirectory, 'video_short.txt'),
+      path: join(transcriptDirectory, 'the_last_man_on_earth.txt'),
       format: 'txt',
       language: 'en'
     }))).to.be.true
 
-    expect(await transcript.read()).to.equal(`You
+    expect(await transcript.read()).to.equal(`December 1965, is that all it has been since I inherited the world only three years, seems like a hundred million.
 `)
   })