File size: 4,111 Bytes
8ad2ab3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
# Define filler words for English, Hindi, Tamil (in both Latin and native scripts)
# Mapping each variant to a common label (usually the Latin script for insight reporting)
FILLER_VARIANTS = {
# English fillers
"um": "um", "uh": "uh", "hmm": "hmm", "ah": "ah", "er": "er",
"umm": "um", "uhh": "uh", "mmm": "hmm",
"like": "like", "you know": "you know", "so": "so", "well": "well",
# Hindi fillers (Devanagari and transliteration)
"मतलब": "matlab", "matlab": "matlab",
"क्या कहते हैं": "kya kehte hain", "kya kehte hain": "kya kehte hain",
"वो ना": "wo na", "woh na": "wo na", "wo na": "wo na",
"ऐसा है": "aisa hai", "aisa hai": "aisa hai",
"हाँ": "haan", "haan": "haan", "हा": "haan", # "हा" might appear as a shorter "haan"
"अच्छा": "acha", "acha": "acha",
# Tamil fillers (Tamil script and transliteration)
"பாத்தீங்கனா": "paatheenga-na", "paatheenga na": "paatheenga-na", "paatheenga-na": "paatheenga-na",
"அப்பரம்": "apparam", "apparam": "apparam",
"என்ன": "enna", "enna": "enna"
}
def detect_fillers(transcript):
"""
Detects filler words in the transcript.
Args:
transcript: Full transcript text
Returns:
tuple: (filler_count, filler_occurrences)
"""
transcript_lower = transcript.lower()
filler_count = 0
# Track which specific fillers were used (for insight examples)
filler_occurrences = {}
for variant, label in FILLER_VARIANTS.items():
if variant in transcript_lower:
count = transcript_lower.count(variant)
if count > 0:
filler_count += count
# Accumulate count for the normalized label
filler_occurrences[label] = filler_occurrences.get(label, 0) + count
return filler_count, filler_occurrences
def analyze_filler_words(filler_count, filler_occurrences, duration):
"""
Analyzes filler word usage in speech.
Args:
filler_count: Total count of filler words
filler_occurrences: Dictionary of specific filler words and their counts
duration: Duration of the audio in seconds
Returns:
dict: Contains the filler words score and insight text
"""
# Extract top examples for insights
filler_examples = []
if filler_occurrences:
# Sort by frequency
sorted_fillers = sorted(filler_occurrences.items(), key=lambda x: x[1], reverse=True)
for label, count in sorted_fillers[:2]:
filler_examples.append(label)
# Compute fillers per minute as a gauge
filler_per_min = (filler_count / duration) * 60.0 if duration > 0 else 0.0
if filler_count == 0:
filler_score = 10
elif filler_per_min < 1:
filler_score = 9
elif filler_per_min < 3:
filler_score = 8
elif filler_per_min < 5:
filler_score = 6
elif filler_per_min < 10:
filler_score = 4
else:
filler_score = 2
filler_score = max(0, filler_score)
# Generate insight text based on the score and examples
if filler_count == 0:
insight = "No filler words (um, ah, etc.) were detected, keeping the speech very clear."
elif filler_count <= 2:
example = filler_examples[0] if filler_examples else "um"
insight = f"Only a couple of filler words (e.g., '{example}') were used, which had minimal impact."
elif filler_count <= 5:
examples = ", ".join(f"'{ex}'" for ex in filler_examples) if filler_examples else "filler words"
insight = f"Some filler words {examples} were used occasionally; reducing them could improve clarity."
else:
examples = ", ".join(f"'{ex}'" for ex in filler_examples) if filler_examples else "'um'"
insight = f"Frequent filler words such as {examples} were detected, which can distract the audience and suggest uncertainty."
return {
"score": int(filler_score),
"insight": insight
} |