Issue with Greek model (el_GR-rapunzelina-low)

[twi252]

Using Piper 1.5.2 under HomeAssistant Supervised (piper runs in Docker). Used tts.speak action routed to piper via its entity to test.

When using the el_GR-rapunzelina-low model in piper and passing an english string for HA/piper to speak via tts to a media speaker, the output sound appears to be English with a French accent.

Test string used was "Hello, how are you?". String read back was in English but with a heavy french accent.

Changing to different models changes the voice, so it is definitely routing through piper, just the voice does not seem to be Greek.

Is the correct model for Greek included (just wondering if maybe it's called Greek but the file may inadvertently be something else?) Or maybe i'm missing something? :)

Hoping to have a tts string provided in English, read out as audio in Greek.

Debug log excerpt:

s6-rc: info: service fix-attrs: starting
s6-rc: info: service fix-attrs successfully started
s6-rc: info: service legacy-cont-init: starting
s6-rc: info: service legacy-cont-init successfully started
s6-rc: info: service piper: starting
s6-rc: info: service piper successfully started
s6-rc: info: service discovery: starting
DEBUG:main:Namespace(piper='/usr/share/piper/piper', voice='el_GR-rapunzelina-low', uri='tcp://0.0.0.0:10200', data_dir=['/data', '/share/piper'], download_dir='/data', speaker='0', noise_scale=0.667, length_scale=1.0, noise_w=0.333, auto_punctuation='.?!', samples_per_chunk=1024, max_piper_procs=1, update_voices=True, debug=True)
DEBUG:wyoming_piper.download:Downloading https://huggingface.co/rhasspy/piper-voices/resolve/v1.0.0/voices.json to /data/voices.json
DEBUG:wyoming_piper.download:Loading /data/voices.json
DEBUG:wyoming_piper.process:Starting process for: el_GR-rapunzelina-low (1/1)
DEBUG:wyoming_piper.download:Checking /data/el_GR-rapunzelina-low.onnx
DEBUG:wyoming_piper.download:Checking /data/el_GR-rapunzelina-low.onnx.json
DEBUG:wyoming_piper.process:Starting piper process: /usr/share/piper/piper args=['--model', '/data/el_GR-rapunzelina-low.onnx', '--config', '/data/el_GR-rapunzelina-low.onnx.json', '--output_dir', '/tmp/tmpkractp63', '--json-input', '--noise-scale', '0.667', '--length-scale', '1.0', '--noise-w', '0.333']
INFO:main:Ready
[17:40:53] INFO: Successfully send discovery information to Home Assistant.
s6-rc: info: service discovery successfully started
s6-rc: info: service legacy-services: starting
s6-rc: info: service legacy-services successfully started
DEBUG:wyoming_piper.handler:Sent info
DEBUG:wyoming_piper.handler:Sent info
DEBUG:wyoming_piper.handler:Sent info
DEBUG:wyoming_piper.handler:Synthesize(text='Hello, how are you?', voice=None)
DEBUG:wyoming_piper.handler:synthesize: raw_text=Hello, how are you?, text='Hello, how are you?'
DEBUG:wyoming_piper.handler:input: {'text': 'Hello, how are you?'}
DEBUG:wyoming_piper.handler:/tmp/tmpkractp73/1736318527335026537.wav
DEBUG:wyoming_piper.handler:Completed request