Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add new tests #1158

Merged
merged 1 commit into from
Nov 20, 2024
Merged

Add new tests #1158

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added tests/data/hotwords.mp3
View file
Open in desktop
Binary file not shown.
120 changes: 120 additions & 0 deletions tests/test_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,120 @@
from faster_whisper import WhisperModel
from faster_whisper.tokenizer import Tokenizer
from faster_whisper.transcribe import get_suppressed_tokens


def test_suppressed_tokens_minus_1():
model = WhisperModel("tiny.en")

tokenizer = Tokenizer(model.hf_tokenizer, False)
tokens = get_suppressed_tokens(tokenizer, [-1])
assert tokens == (
1,
2,
7,
8,
9,
10,
14,
25,
26,
27,
28,
29,
31,
58,
59,
60,
61,
62,
63,
90,
91,
92,
93,
357,
366,
438,
532,
685,
705,
796,
930,
1058,
1220,
1267,
1279,
1303,
1343,
1377,
1391,
1635,
1782,
1875,
2162,
2361,
2488,
3467,
4008,
4211,
4600,
4808,
5299,
5855,
6329,
7203,
9609,
9959,
10563,
10786,
11420,
11709,
11907,
13163,
13697,
13700,
14808,
15306,
16410,
16791,
17992,
19203,
19510,
20724,
22305,
22935,
27007,
30109,
30420,
33409,
34949,
40283,
40493,
40549,
47282,
49146,
50257,
50357,
50358,
50359,
50360,
)


def test_suppressed_tokens_minus_value():
model = WhisperModel("tiny.en")

tokenizer = Tokenizer(model.hf_tokenizer, False)
tokens = get_suppressed_tokens(tokenizer, [13])
assert tokens == (13, 50257, 50357, 50358, 50359, 50360)


def test_split_on_unicode():
model = WhisperModel("tiny")
tokenizer = Tokenizer(model.hf_tokenizer, False)

tokens = [8404, 871, 287, 6, 246, 526, 3210, 20378]
words, word_tokens = tokenizer.split_tokens_on_unicode(tokens)

assert words == [" elle", " est", " l", "'", "\ufffd", "é", "rit", "oire"]
assert word_tokens == [[8404], [871], [287], [6], [246], [526], [3210], [20378]]
152 changes: 51 additions & 101 deletions tests/test_transcribe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,9 @@
import inspect
import os

import numpy as np

from faster_whisper import BatchedInferencePipeline, WhisperModel, decode_audio
from faster_whisper.tokenizer import Tokenizer
from faster_whisper.transcribe import get_suppressed_tokens


def test_supported_languages():
Expand Down Expand Up @@ -215,107 +214,58 @@ def test_multilingual_transcription(data_dir):
)


def test_suppressed_tokens_minus_1():
model = WhisperModel("tiny.en")
def test_hotwords(data_dir):
model = WhisperModel("tiny")
pipeline = BatchedInferencePipeline(model)

audio_path = os.path.join(data_dir, "hotwords.mp3")
audio = decode_audio(audio_path)

segments, info = model.transcribe(audio, hotwords="ComfyUI")
segments = list(segments)

assert "ComfyUI" in segments[0].text
assert info.transcription_options.hotwords == "ComfyUI"

segments, info = pipeline.transcribe(audio, hotwords="ComfyUI")
segments = list(segments)

assert "ComfyUI" in segments[0].text
assert info.transcription_options.hotwords == "ComfyUI"

tokenizer = Tokenizer(model.hf_tokenizer, False)
tokens = get_suppressed_tokens(tokenizer, [-1])
assert tokens == (
1,
2,
7,
8,
9,
10,
14,
25,
26,
27,
28,
29,
31,
58,
59,
60,
61,
62,
63,
90,
91,
92,
93,
357,
366,
438,
532,
685,
705,
796,
930,
1058,
1220,
1267,
1279,
1303,
1343,
1377,
1391,
1635,
1782,
1875,
2162,
2361,
2488,
3467,
4008,
4211,
4600,
4808,
5299,
5855,
6329,
7203,
9609,
9959,
10563,
10786,
11420,
11709,
11907,
13163,
13697,
13700,
14808,
15306,
16410,
16791,
17992,
19203,
19510,
20724,
22305,
22935,
27007,
30109,
30420,
33409,
34949,
40283,
40493,
40549,
47282,
49146,
50257,
50357,
50358,
50359,
50360,

def test_transcribe_signature():
model_transcribe_args = set(inspect.getargs(WhisperModel.transcribe.__code__).args)
pipeline_transcribe_args = set(
inspect.getargs(BatchedInferencePipeline.transcribe.__code__).args
)
pipeline_transcribe_args.remove("batch_size")

assert model_transcribe_args == pipeline_transcribe_args

def test_suppressed_tokens_minus_value():
model = WhisperModel("tiny.en")

tokenizer = Tokenizer(model.hf_tokenizer, False)
tokens = get_suppressed_tokens(tokenizer, [13])
assert tokens == (13, 50257, 50357, 50358, 50359, 50360)
def test_monotonic_timestamps(physcisworks_path):
model = WhisperModel("tiny")
pipeline = BatchedInferencePipeline(model=model)

segments, info = model.transcribe(physcisworks_path, word_timestamps=True)
segments = list(segments)

for i in range(len(segments) - 1):
assert segments[i].start <= segments[i].end
assert segments[i].end <= segments[i + 1].start
for word in segments[i].words:
assert word.start <= word.end
assert word.end <= segments[i].end
assert segments[-1].end <= info.duration

segments, info = pipeline.transcribe(physcisworks_path, word_timestamps=True)
segments = list(segments)

for i in range(len(segments) - 1):
assert segments[i].start <= segments[i].end
assert segments[i].end <= segments[i + 1].start
for word in segments[i].words:
assert word.start <= word.end
assert word.end <= segments[i].end
assert segments[-1].end <= info.duration
Loading