changed all kaldi-nl-test refs to whisper-test

beeldengeluid · Sep 23, 2024 · a837df6 · a837df6
1 parent 147d4dc
commit a837df6
Show file tree

Hide file tree

Showing 6 changed files with 7 additions and 7 deletions.
diff --git a/.env b/.env
@@ -1,5 +1,5 @@
 # passed to --input-uri (see main.py)
-INPUT_URI=http://model-hosting.beng.nl/kaldi-nl-test.mp3
+INPUT_URI=http://model-hosting.beng.nl/whisper-test.mp3
 
 # passed to --output-uri (see main.py)
 OUTPUT_URI=s3://x-omg-daan-av/assets/2101608150135908031__NOS_JOURNAAL_-WON01207359/

diff --git a/.gitignore b/.gitignore
@@ -2,11 +2,11 @@
 !/data/README.md
 !/data/input/
 /data/input/*
-!/data/input/kaldi-nl-test.mp3
+!/data/input/whisper-test.mp3
 !/data/output
 /data/output/*
-!/data/output/kaldi-nl-test
-!/data/output/kaldi-nl-test/*
+!/data/output/whisper-test
+!/data/output/whisper-test/*
 /model/*
 __pycache__
 .pytest_cache

diff --git a/daan_transcript.py b/daan_transcript.py
@@ -18,7 +18,7 @@ class ParsedResult(TypedDict):
     carrierId: str
 
 
-# asr_output_dir e.g /data/output/kaldi-nl-test/
+# asr_output_dir e.g /data/output/whisper-test/
 def generate_daan_transcript(asr_output_dir: str) -> bool:
     logger.info(f"Generating transcript from: {asr_output_dir}")
     whisper_transcript = load_whisper_transcript(asr_output_dir)

diff --git a/data/input/kaldi-nl-test.mp3 → data/input/whisper-test.mp3 b/data/input/kaldi-nl-test.mp3 → data/input/whisper-test.mp3
diff --git a/...put/kaldi-nl-test/daan-es-transcript.json → ...tput/whisper-test/daan-es-transcript.json b/...put/kaldi-nl-test/daan-es-transcript.json → ...tput/whisper-test/daan-es-transcript.json
@@ -22,6 +22,6 @@
         "start": 3.22,
         "fragmentId": "00000",
         "words": "En dat je er bent, ben je voor het eerst hierof, ben je al de kef.",
-        "carrierId": "kaldi-nl-test"
+        "carrierId": "whisper-test"
     }
 ]
diff --git a/...put/kaldi-nl-test/whisper-transcript.json → ...tput/whisper-test/whisper-transcript.json b/...put/kaldi-nl-test/whisper-transcript.json → ...tput/whisper-test/whisper-transcript.json
@@ -1,5 +1,5 @@
 {
-    "carrierId": "kaldi-nl-test",
+    "carrierId": "whisper-test",
     "segments": [
         {
             "id": 1,