SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add language to word timestamps for Whisper (#31572)

Browse Source 
* add language to words

_collate_word_timestamps uses the return_language flag to determine whether the language of the chunk should be added to the word's information

* ran style checks

added missing comma

* add new language test

test that the pipeline can return both the language and timestamp

* remove model configuration in test

Removed model configurations that do not influence test results

* remove model configuration in test

Removed model configurations that do not influence test results
This commit is contained in:
Robin Bakker
2024-07-17 22:32:53 +02:00
committed by GitHub
parent cb23d1b20b
commit b31d595040
2 changed files with 66 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
tests/pipelines/test_pipelines_automatic_speech_recognition.py
View File

@@ -322,7 +322,6 @@ class AutomaticSpeechRecognitionPipelineTests(unittest.TestCase):
@slow
@require_torch
@slow
def test_return_timestamps_in_preprocess(self):
pipe = pipeline(
task="automatic-speech-recognition",
@@ -332,10 +331,10 @@ class AutomaticSpeechRecognitionPipelineTests(unittest.TestCase):
)
data = load_dataset("openslr/librispeech_asr", "clean", split="test", streaming=True, trust_remote_code=True)
sample = next(iter(data))
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="en", task="transcribe")
res = pipe(sample["audio"]["array"])
self.assertEqual(res, {"text": " Conquered returned to its place amidst the tents."})
res = pipe(sample["audio"]["array"], return_timestamps=True)
self.assertEqual(
res,
@@ -344,9 +343,8 @@ class AutomaticSpeechRecognitionPipelineTests(unittest.TestCase):
"chunks": [{"timestamp": (0.0, 3.36), "text": " Conquered returned to its place amidst the tents."}],
},
)
pipe.model.generation_config.alignment_heads = [[2, 2], [3, 0], [3, 2], [3, 3], [3, 4], [3, 5]]
res = pipe(sample["audio"]["array"], return_timestamps="word")
res = pipe(sample["audio"]["array"], return_timestamps="word")
# fmt: off
self.assertEqual(
res,
@@ -366,6 +364,63 @@ class AutomaticSpeechRecognitionPipelineTests(unittest.TestCase):
)
# fmt: on
@slow
@require_torch
def test_return_timestamps_and_language_in_preprocess(self):
pipe = pipeline(
task="automatic-speech-recognition",
model="openai/whisper-tiny",
chunk_length_s=8,
stride_length_s=1,
return_language=True,
)
data = load_dataset("openslr/librispeech_asr", "clean", split="test", streaming=True, trust_remote_code=True)
sample = next(iter(data))
res = pipe(sample["audio"]["array"])
self.assertEqual(
res,
{
"text": " Conquered returned to its place amidst the tents.",
"chunks": [{"language": "english", "text": " Conquered returned to its place amidst the tents."}],
},
)
res = pipe(sample["audio"]["array"], return_timestamps=True)
self.assertEqual(
res,
{
"text": " Conquered returned to its place amidst the tents.",
"chunks": [
{
"timestamp": (0.0, 3.36),
"language": "english",
"text": " Conquered returned to its place amidst the tents.",
}
],
},
)
res = pipe(sample["audio"]["array"], return_timestamps="word")
# fmt: off
self.assertEqual(
res,
{
'text': ' Conquered returned to its place amidst the tents.',
'chunks': [
{"language": "english",'text': ' Conquered', 'timestamp': (0.5, 1.2)},
{"language": "english", 'text': ' returned', 'timestamp': (1.2, 1.64)},
{"language": "english",'text': ' to', 'timestamp': (1.64, 1.84)},
{"language": "english",'text': ' its', 'timestamp': (1.84, 2.02)},
{"language": "english",'text': ' place', 'timestamp': (2.02, 2.28)},
{"language": "english",'text': ' amidst', 'timestamp': (2.28, 2.8)},
{"language": "english",'text': ' the', 'timestamp': (2.8, 2.98)},
{"language": "english",'text': ' tents.', 'timestamp': (2.98, 3.48)},
],
},
)
# fmt: on
@slow
@require_torch
def test_return_timestamps_in_preprocess_longform(self):