valenti/spark-pocket-tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Do not use auth in the CI (#53)

Browse Source 
Allows anyone to run the CI
This commit is contained in:
Gabriel de Marmiesse
2026-01-17 14:58:36 +01:00
committed by GitHub
parent f8f25eac00
commit 636ec2360d
3 changed files with 18 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_documentation_examples.py
+11 -22
View File
@@ -10,9 +10,7 @@ def test_readme_example():
from pocket_tts import TTSModel
tts_model = TTSModel.load_model()
voice_state = tts_model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
voice_state = tts_model.get_state_for_audio_prompt("cosette")
audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.")
# Audio is a torch tensor containing PCM data.
scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy())
@@ -27,9 +25,7 @@ def test_quick_start():
tts_model = TTSModel.load_model()
# Get voice state from an audio file
voice_state = tts_model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
voice_state = tts_model.get_state_for_audio_prompt("marius")
# Generate audio
audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.")
@@ -79,6 +75,9 @@ def test_get_state_for_audio_prompt():
from pocket_tts import TTSModel
model = TTSModel.load_model()
# hack to make it work without auth
model.has_voice_cloning = True
# From HuggingFace URL
voice_state = model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
@@ -99,9 +98,7 @@ def test_generate_audio():
model = TTSModel.load_model()
voice_state = model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
voice_state = model.get_state_for_audio_prompt("marius")
# Generate audio
audio = model.generate_audio(voice_state, "Hello world!", frames_after_eos=2, copy_state=True)
@@ -115,9 +112,7 @@ def test_generate_audio_stream():
model = TTSModel.load_model()
voice_state = model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
voice_state = model.get_state_for_audio_prompt("fantine")
# Stream generation
for chunk in model.generate_audio_stream(voice_state, "Long text content..."):
# Process each chunk as it's generated
@@ -131,17 +126,13 @@ def test_voice_management():
model = TTSModel.load_model()
# Preload multiple voices
voices = {
"casual": model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
),
"funny": model.get_state_for_audio_prompt(
"https://huggingface.co/kyutai/tts-voices/resolve/main/expresso/ex01-ex02_default_001_channel1_168s.wav"
),
"casual": model.get_state_for_audio_prompt("alba"),
"serious": model.get_state_for_audio_prompt("marius"),
}
# Generate with different voices
casual_audio = model.generate_audio(voices["casual"], "Hey there!")
funny_audio = model.generate_audio(voices["funny"], "Good morning.")
funny_audio = model.generate_audio(voices["serious"], "Good morning.")
def test_batch_processing():
@@ -152,9 +143,7 @@ def test_batch_processing():
model = TTSModel.load_model()
voice_state = model.get_state_for_audio_prompt(
"hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)
voice_state = model.get_state_for_audio_prompt("azelma")
# Process multiple texts efficiently by re-using the same voice state
texts = [
"First sentence to generate.",