Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-24 14:35:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Delete timestamps test

Browse Source
This commit is contained in:
PiotrBLL 2024-11-12 20:10:49 +01:00
parent 866fece681
commit 3e826a2aff
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/test_transcribe.py
View File

@ -51,7 +51,7 @@ def test_transcribe_hpu(model_name: str):
language = "en" if model_name.endswith(".en") else None language = "en" if model_name.endswith(".en") else None
result = model.transcribe( result = model.transcribe(
audio_path, language=language, temperature=0.0, word_timestamps=True audio_path, language=language, temperature=0.0
) )
assert result["language"] == "en" assert result["language"] == "en"
assert result["text"] == "".join([s["text"] for s in result["segments"]]) assert result["text"] == "".join([s["text"] for s in result["segments"]])
@ -64,7 +64,6 @@ def test_transcribe_hpu(model_name: str):
tokenizer = get_tokenizer(model.is_multilingual, num_languages=model.num_languages) tokenizer = get_tokenizer(model.is_multilingual, num_languages=model.num_languages)
all_tokens = [t for s in result["segments"] for t in s["tokens"]] all_tokens = [t for s in result["segments"] for t in s["tokens"]]
assert tokenizer.decode(all_tokens) == result["text"] assert tokenizer.decode(all_tokens) == result["text"]
assert tokenizer.decode_with_timestamps(all_tokens).startswith("<|0.00|>")
timing_checked = False timing_checked = False
for segment in result["segments"]: for segment in result["segments"]: