API¶

malaysia_ai_projects¶

malaysia_ai_projects.jelapang_padi¶

malaysia_ai_projects.jelapang_padi.available_model()[source]¶: List available Jelapang Padi models.

malaysia_ai_projects.jelapang_padi.load(model: str = 'efficientnet-b2', **kwargs)[source]¶

Load Jelapang Padi model.

Parameters

model (str, optional (default='efficientnet-b2')) –

Model architecture supported. Allowed values:

'efficientnet-b4' - EfficientNet B4 + Unet.
'efficientnet-b4-quantized' - EfficientNet B4 + Unet with dynamic quantized.
'efficientnet-b2' - EfficientNet B2 + Unet.
'efficientnet-b2-quantized' - EfficientNet B2 + Unet with dynamic quantized.

Returns

result

Return type

malaysia_ai_projects.jelapang_padi.Model class

malaysia_ai_projects.jelapang_padi.Model¶

class malaysia_ai_projects.jelapang_padi.Model[source]¶

predict(inputs: List[numpy.array])[source]¶

Parameters: input (List[np.array]) – List of np.array, should be size [H, W, 3], H and W can be dynamic.
Returns: result
Return type: List[np.array]

malaysia_ai_projects.malay_vits¶

malaysia_ai_projects.malay_vits.put_spacing_num(string)[source]¶: ‘ni1996’ -> ‘ni 1996’

malaysia_ai_projects.malay_vits.available_model()[source]¶: List available Malay VITS models.

malaysia_ai_projects.malay_vits.load(model: str = 'osman')[source]¶

Load Malay VITS model.

Parameters

model (str, optional (default='osman')) –

Model architecture supported. Allowed values:

'osman' - VITS Osman speaker, https://huggingface.co/malay-huggingface/VITS-Osman
'yasmin' - VITS Yasmin speaker, https://huggingface.co/malay-huggingface/VITS-Yasmin

Returns

result

Return type

malaysia_ai_projects.malay_vits.Model class

malaysia_ai_projects.malay_vits.Model¶

class malaysia_ai_projects.malay_vits.Model[source]¶

predict(input: str, noise_scale: float = 0.667, noise_scale_w: float = 0.8, length_scale: float = 1.0, norm_function: Callable = None)[source]¶

Parameters

input (str) –
noise_scale (float, optional (default=0.667)) –
noise_scale_w (float, optional (default=0.8)) –
length_scale (float, optional (default=1.0)) –
norm_function (Callable, optional (default=None)) –

Returns

result

Return type

(audio with 22050 sample rate, text, list of chars, alignment)

malaysia_ai_projects.pembalakan¶

malaysia_ai_projects.pembalakan.available_model()[source]¶: List available Pembalakan models.

malaysia_ai_projects.pembalakan.load(model: str = 'efficientnet-b2', **kwargs)[source]¶

Load Pembalakan model.

Parameters

model (str, optional (default='efficientnet-b2')) –

Model architecture supported. Allowed values:

'efficientnet-b4' - EfficientNet B4 + Unet.
'efficientnet-b4-quantized' - EfficientNet B4 + Unet with dynamic quantized.
'efficientnet-b2' - EfficientNet B2 + Unet.
'efficientnet-b2-quantized' - EfficientNet B2 + Unet with dynamic quantized.

Returns

result

Return type

malaysia_ai_projects.pembalakan.Model class

malaysia_ai_projects.pembalakan.Model¶

class malaysia_ai_projects.pembalakan.Model[source]¶

predict(inputs: List[numpy.array])[source]¶

Parameters: input (List[np.array]) – List of np.array, should be size [H, W, 3], H and W can be dynamic.
Returns: result
Return type: List[np.array]

malaysia_ai_projects.suarakami¶

malaysia_ai_projects.suarakami.available_model()[source]¶: List available SuaraKami models.

malaysia_ai_projects.suarakami.available_lm()[source]¶: List available SuaraKami language models.

malaysia_ai_projects.suarakami.load(model: str = 'small-conformer', lm: str = None)[source]¶

Load suarakami model.

Parameters

model (str, optional (default='small-conformer')) –
Model architecture supported. Allowed values:
- 'small-conformer' - Small Conformer model.
lm (str, optional (default=None)) –
Language Model supported. Allowed values:
- None - No Language Model will use.
- 'v1-lm' - Will use V1 Language Model, size ~800 MB.

Returns

result

Return type

malaysia_ai_projects.suarakami.Model class

malaysia_ai_projects.suarakami.Model¶

class malaysia_ai_projects.suarakami.Model[source]¶

predict(input: numpy.array)[source]¶

Parameters: input (np.array) – np.array, must in 16k rate, prefer from librosa.load(file,16_000).
Returns: result
Return type: text, entropy, timesteps