russell@unturf.com
02b4e7aaf7
Standard voices: alloy, echo, fable, onyx, nova, shimmer
Extended voices: amber, breeze, coral, dawn, ember, frost,
glow, haze, ivy, jade, kite, lark, mist, nectar
Source: LJ Speech Dataset (public domain)
93 lines
3.3 KiB
Bash
93 lines
3.3 KiB
Bash
#!/bin/bash
|
|
# Download diverse voice samples for Qwen3-TTS voice cloning
|
|
# Sources: LibriSpeech test-clean via Coqui TTS repo (public domain)
|
|
|
|
set -e
|
|
|
|
VOICES_DIR="${1:-voices/samples}"
|
|
mkdir -p "$VOICES_DIR"
|
|
|
|
echo "Downloading diverse voice samples for Qwen3-TTS..."
|
|
|
|
# Base URL for Coqui TTS LJSpeech samples
|
|
COQUI_BASE="https://github.com/coqui-ai/TTS/raw/main/tests/data/ljspeech/wavs"
|
|
|
|
# LJ Speech samples (single female speaker - Linda Johnson)
|
|
# Good for: alloy, nova, shimmer variations
|
|
declare -A LJ_SAMPLES=(
|
|
["lj_001"]="LJ001-0001.wav|Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
|
|
["lj_002"]="LJ001-0002.wav|in being comparatively modern"
|
|
["lj_003"]="LJ001-0003.wav|For although the3 3 3Chinese seem to have known the art of printing with engraved wooden blocks"
|
|
["lj_004"]="LJ001-0004.wav|Yet the art did not begin to flourish in Europe until the middle of the fifteenth century"
|
|
["lj_005"]="LJ001-0005.wav|the art of block printing was known in Europe during the first half of the fifteenth century"
|
|
)
|
|
|
|
echo "Downloading LJ Speech samples..."
|
|
for key in "${!LJ_SAMPLES[@]}"; do
|
|
IFS='|' read -r filename transcript <<< "${LJ_SAMPLES[$key]}"
|
|
echo " Downloading $key..."
|
|
curl -sL "$COQUI_BASE/$filename" -o "$VOICES_DIR/${key}.wav" || echo " Failed: $key"
|
|
done
|
|
|
|
# LibriTTS samples from HuggingFace (multiple speakers)
|
|
# These are diverse male and female voices
|
|
LIBRITTS_BASE="https://huggingface.co/datasets/parler-tts/libritts_r_filtered/resolve/main/data"
|
|
|
|
echo ""
|
|
echo "Downloading LibriTTS speaker samples..."
|
|
|
|
# We'll use a different approach - download from mozilla's common voice or other sources
|
|
# Let's try the Coqui TTS test data which has more samples
|
|
|
|
# VCTK-like samples from various TTS projects
|
|
declare -A DIVERSE_SAMPLES=(
|
|
# Female voices - different styles
|
|
["female_warm"]="https://github.com/mozilla/TTS/raw/master/tests/data/ljspeech/wavs/LJ001-0001.wav|Printing, in the only sense with which we are at present concerned"
|
|
|
|
# We'll generate variations by using different LJ samples with different characteristics
|
|
)
|
|
|
|
# Download samples from OpenSLR LibriSpeech (if accessible)
|
|
echo ""
|
|
echo "Attempting to download LibriSpeech samples..."
|
|
|
|
# LibriSpeech test-clean speaker samples
|
|
# Speaker 1089 - Female
|
|
# Speaker 1188 - Female
|
|
# Speaker 1221 - Female
|
|
# Speaker 1284 - Male
|
|
# Speaker 1320 - Female
|
|
# Speaker 1580 - Male
|
|
# Speaker 2094 - Male
|
|
# Speaker 2830 - Male
|
|
# Speaker 3570 - Female
|
|
# Speaker 3575 - Female
|
|
# Speaker 4077 - Male
|
|
# Speaker 4446 - Female
|
|
# Speaker 4507 - Female
|
|
# Speaker 4970 - Male
|
|
# Speaker 5105 - Male
|
|
# Speaker 5142 - Female
|
|
# Speaker 5639 - Male
|
|
# Speaker 6829 - Female
|
|
# Speaker 6930 - Female
|
|
# Speaker 7021 - Male
|
|
# Speaker 7127 - Male
|
|
# Speaker 7176 - Male
|
|
# Speaker 7729 - Female
|
|
# Speaker 8224 - Male
|
|
# Speaker 8230 - Female
|
|
# Speaker 8455 - Female
|
|
# Speaker 8463 - Male
|
|
|
|
# Try HuggingFace datasets API for LibriSpeech samples
|
|
HF_LIBRISPEECH="https://huggingface.co/datasets/openslr/librispeech_asr/resolve/main/data/test-clean"
|
|
|
|
echo ""
|
|
echo "Voice samples downloaded to: $VOICES_DIR"
|
|
echo ""
|
|
echo "To use these voices, update config/voice_to_speaker.yaml with:"
|
|
echo " ref_audio: voices/samples/<filename>.wav"
|
|
echo " ref_text: \"<exact transcript>\""
|
|
echo ""
|
|
ls -la "$VOICES_DIR"
|