Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -7,82 +7,82 @@ import evaluate
|
|
| 7 |
|
| 8 |
# Example prompts from the paper
|
| 9 |
EXAMPLES = [
|
| 10 |
-
# Each
|
| 11 |
-
|
| 12 |
"A man speaks with a booming, medium-pitched voice in a clear environment, delivering his words at a measured speed.",
|
| 13 |
"That's my brother. I do agree, though, it wasn't very well-groomed.",
|
| 14 |
1.5, 3, 20.0
|
| 15 |
-
|
| 16 |
-
|
| 17 |
"A male speaker's speech is distinguished by a slurred articulation, delivered at a measured pace in a clear environment.",
|
| 18 |
"reveal my true intentions in different ways. That's why the Street King Project and SMS",
|
| 19 |
1.5, 3, 20.0
|
| 20 |
-
|
| 21 |
-
|
| 22 |
"In a clear environment, a male speaker delivers his words hesitantly with a measured pace.",
|
| 23 |
"the Grand Slam tennis game has sort of taken over our set that's sort of all the way",
|
| 24 |
1.5, 3, 20.0
|
| 25 |
-
|
| 26 |
-
|
| 27 |
"A low-pitched, guttural male voice speaks slowly in a clear environment.",
|
| 28 |
"you know you want to see how far you can push everything and as an artist",
|
| 29 |
1.5, 3, 20.0
|
| 30 |
-
|
| 31 |
-
|
| 32 |
"A man speaks with a measured pace in a clear environment, displaying a distinct British accent.",
|
| 33 |
"most important but the reaction is very similar throughout the world it's really very very similar",
|
| 34 |
1.5, 3, 20.0
|
| 35 |
-
|
| 36 |
-
|
| 37 |
"A male speaker's voice is clear and delivered at a measured pace in a quiet environment. His speech carries a distinct Jamaican accent.",
|
| 38 |
"about God and the people him come from is more Christian, you know. We always",
|
| 39 |
1.5, 3, 20.0
|
| 40 |
-
|
| 41 |
-
|
| 42 |
"In a clear environment, a male voice speaks with a sad tone.",
|
| 43 |
"Was that your landlord?",
|
| 44 |
1.5, 3, 20.0
|
| 45 |
-
|
| 46 |
-
|
| 47 |
"A man speaks with a measured pace in a clear environment, his voice carrying a sleepy tone.",
|
| 48 |
"I mean, to be fair, I did see a UFO, so, you know.",
|
| 49 |
1.5, 3, 20.0
|
| 50 |
-
|
| 51 |
-
|
| 52 |
"A frightened woman speaks with a clear and distinct voice.",
|
| 53 |
"Yes, that's what they said. I don't know what you're getting done. What are you getting done? Oh, okay. Yeah.",
|
| 54 |
1.5, 3, 20.0
|
| 55 |
-
|
| 56 |
-
|
| 57 |
"A woman speaks slowly in a clear environment, her voice filled with awe.",
|
| 58 |
"Oh wow, this music is fantastic. You play so well. I could just sit here.",
|
| 59 |
1.5, 3, 20.0
|
| 60 |
-
|
| 61 |
-
|
| 62 |
"A woman speaks with a high-pitched voice in a clear environment, conveying a sense of anxiety.",
|
| 63 |
"this is just way too overwhelming. I literally don't know how I'm going to get any of this done on time. I feel so overwhelmed right now. No one is helping me. Everyone's ignoring my calls and my emails. I don't know what I'm supposed to do right now.",
|
| 64 |
1.5, 3, 20.0
|
| 65 |
-
|
| 66 |
-
|
| 67 |
"A female speaker's high-pitched voice is clear and carries over a laughing, unobstructed environment.",
|
| 68 |
"What is wrong with him, Chad?",
|
| 69 |
1.5, 3, 20.0
|
| 70 |
-
|
| 71 |
-
|
| 72 |
"In a clear environment, a man speaks in a whispered tone.",
|
| 73 |
"The fruit piece, the still lifes, you mean.",
|
| 74 |
1.5, 3, 20.0
|
| 75 |
-
|
| 76 |
-
|
| 77 |
"A male speaker with a husky, low-pitched voice delivers clear speech in a quiet environment.",
|
| 78 |
"Ari had to somehow be subservient to Lloyd that would be unbelievable like if Lloyd was the guy who was like running Time Warner you know what I mean like",
|
| 79 |
1.5, 3, 20.0
|
| 80 |
-
|
| 81 |
-
|
| 82 |
"A female speaker's voice is clear and expressed at a measured pace, but carries a high-pitched, nasal tone, recorded in a quiet environment.",
|
| 83 |
"You know, Joe Bow, hockey mom from Wasilla, if I have an idea that would perhaps make",
|
| 84 |
1.5, 3, 20.0
|
| 85 |
-
|
| 86 |
]
|
| 87 |
|
| 88 |
def wer(asr_pipeline, prompt, audio, sampling_rate):
|
|
@@ -317,4 +317,4 @@ def create_demo():
|
|
| 317 |
|
| 318 |
if __name__ == "__main__":
|
| 319 |
demo = create_demo()
|
| 320 |
-
demo.launch(share=True)
|
|
|
|
| 7 |
|
| 8 |
# Example prompts from the paper
|
| 9 |
EXAMPLES = [
|
| 10 |
+
# Each list is [description, text, guidance_scale, num_retries, wer_threshold]
|
| 11 |
+
[
|
| 12 |
"A man speaks with a booming, medium-pitched voice in a clear environment, delivering his words at a measured speed.",
|
| 13 |
"That's my brother. I do agree, though, it wasn't very well-groomed.",
|
| 14 |
1.5, 3, 20.0
|
| 15 |
+
],
|
| 16 |
+
[
|
| 17 |
"A male speaker's speech is distinguished by a slurred articulation, delivered at a measured pace in a clear environment.",
|
| 18 |
"reveal my true intentions in different ways. That's why the Street King Project and SMS",
|
| 19 |
1.5, 3, 20.0
|
| 20 |
+
],
|
| 21 |
+
[
|
| 22 |
"In a clear environment, a male speaker delivers his words hesitantly with a measured pace.",
|
| 23 |
"the Grand Slam tennis game has sort of taken over our set that's sort of all the way",
|
| 24 |
1.5, 3, 20.0
|
| 25 |
+
],
|
| 26 |
+
[
|
| 27 |
"A low-pitched, guttural male voice speaks slowly in a clear environment.",
|
| 28 |
"you know you want to see how far you can push everything and as an artist",
|
| 29 |
1.5, 3, 20.0
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
"A man speaks with a measured pace in a clear environment, displaying a distinct British accent.",
|
| 33 |
"most important but the reaction is very similar throughout the world it's really very very similar",
|
| 34 |
1.5, 3, 20.0
|
| 35 |
+
],
|
| 36 |
+
[
|
| 37 |
"A male speaker's voice is clear and delivered at a measured pace in a quiet environment. His speech carries a distinct Jamaican accent.",
|
| 38 |
"about God and the people him come from is more Christian, you know. We always",
|
| 39 |
1.5, 3, 20.0
|
| 40 |
+
],
|
| 41 |
+
[
|
| 42 |
"In a clear environment, a male voice speaks with a sad tone.",
|
| 43 |
"Was that your landlord?",
|
| 44 |
1.5, 3, 20.0
|
| 45 |
+
],
|
| 46 |
+
[
|
| 47 |
"A man speaks with a measured pace in a clear environment, his voice carrying a sleepy tone.",
|
| 48 |
"I mean, to be fair, I did see a UFO, so, you know.",
|
| 49 |
1.5, 3, 20.0
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
"A frightened woman speaks with a clear and distinct voice.",
|
| 53 |
"Yes, that's what they said. I don't know what you're getting done. What are you getting done? Oh, okay. Yeah.",
|
| 54 |
1.5, 3, 20.0
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
"A woman speaks slowly in a clear environment, her voice filled with awe.",
|
| 58 |
"Oh wow, this music is fantastic. You play so well. I could just sit here.",
|
| 59 |
1.5, 3, 20.0
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
"A woman speaks with a high-pitched voice in a clear environment, conveying a sense of anxiety.",
|
| 63 |
"this is just way too overwhelming. I literally don't know how I'm going to get any of this done on time. I feel so overwhelmed right now. No one is helping me. Everyone's ignoring my calls and my emails. I don't know what I'm supposed to do right now.",
|
| 64 |
1.5, 3, 20.0
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
"A female speaker's high-pitched voice is clear and carries over a laughing, unobstructed environment.",
|
| 68 |
"What is wrong with him, Chad?",
|
| 69 |
1.5, 3, 20.0
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
"In a clear environment, a man speaks in a whispered tone.",
|
| 73 |
"The fruit piece, the still lifes, you mean.",
|
| 74 |
1.5, 3, 20.0
|
| 75 |
+
],
|
| 76 |
+
[
|
| 77 |
"A male speaker with a husky, low-pitched voice delivers clear speech in a quiet environment.",
|
| 78 |
"Ari had to somehow be subservient to Lloyd that would be unbelievable like if Lloyd was the guy who was like running Time Warner you know what I mean like",
|
| 79 |
1.5, 3, 20.0
|
| 80 |
+
],
|
| 81 |
+
[
|
| 82 |
"A female speaker's voice is clear and expressed at a measured pace, but carries a high-pitched, nasal tone, recorded in a quiet environment.",
|
| 83 |
"You know, Joe Bow, hockey mom from Wasilla, if I have an idea that would perhaps make",
|
| 84 |
1.5, 3, 20.0
|
| 85 |
+
]
|
| 86 |
]
|
| 87 |
|
| 88 |
def wer(asr_pipeline, prompt, audio, sampling_rate):
|
|
|
|
| 317 |
|
| 318 |
if __name__ == "__main__":
|
| 319 |
demo = create_demo()
|
| 320 |
+
demo.launch(share=True)
|