add requested changes from code review
This commit is contained in:
@@ -9,7 +9,6 @@ import os
|
|||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
|
||||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||||
|
|||||||
@@ -40,18 +40,18 @@ class HathoraSTTService(SegmentedSTTService):
|
|||||||
config: Some models support additional config, refer to
|
config: Some models support additional config, refer to
|
||||||
[docs](https://models.hathora.dev) for each model to see
|
[docs](https://models.hathora.dev) for each model to see
|
||||||
what is supported.
|
what is supported.
|
||||||
base_url: Base API URL for the Hathora STT service.
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
language: Optional[str] = None
|
language: Optional[str] = None
|
||||||
config: Optional[list[ConfigOption]] = None
|
config: Optional[list[ConfigOption]] = None
|
||||||
base_url: str = "https://api.models.hathora.dev/inference/v1/stt",
|
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
*,
|
*,
|
||||||
model: str,
|
model: str,
|
||||||
|
sample_rate: Optional[int] = None,
|
||||||
api_key: Optional[str] = None,
|
api_key: Optional[str] = None,
|
||||||
|
base_url: str = "https://api.models.hathora.dev/inference/v1/stt",
|
||||||
params: Optional[InputParams] = None,
|
params: Optional[InputParams] = None,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
):
|
):
|
||||||
@@ -60,17 +60,21 @@ class HathoraSTTService(SegmentedSTTService):
|
|||||||
Args:
|
Args:
|
||||||
model: Model to use; find available models
|
model: Model to use; find available models
|
||||||
[here](https://models.hathora.dev).
|
[here](https://models.hathora.dev).
|
||||||
|
sample_rate: The sample rate for audio input. If None, will be determined
|
||||||
|
from the start frame.
|
||||||
api_key: API key for authentication with the Hathora service;
|
api_key: API key for authentication with the Hathora service;
|
||||||
provision one [here](https://models.hathora.dev/tokens).
|
provision one [here](https://models.hathora.dev/tokens).
|
||||||
|
base_url: Base API URL for the Hathora STT service.
|
||||||
params: Configuration parameters.
|
params: Configuration parameters.
|
||||||
**kwargs: Additional arguments passed to the parent class.
|
**kwargs: Additional arguments passed to the parent class.
|
||||||
"""
|
"""
|
||||||
super().__init__(
|
super().__init__(
|
||||||
|
sample_rate=sample_rate,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
)
|
)
|
||||||
self._model = model
|
self._model = model
|
||||||
self._api_key = api_key or os.getenv("HATHORA_API_KEY")
|
self._api_key = api_key or os.getenv("HATHORA_API_KEY")
|
||||||
self._base_url = params.base_url
|
self._base_url = base_url
|
||||||
|
|
||||||
params = params or HathoraSTTService.InputParams()
|
params = params or HathoraSTTService.InputParams()
|
||||||
|
|
||||||
|
|||||||
@@ -59,19 +59,19 @@ class HathoraTTSService(TTSService):
|
|||||||
config: Some models support additional config, refer to
|
config: Some models support additional config, refer to
|
||||||
[docs](https://models.hathora.dev) for each model to see
|
[docs](https://models.hathora.dev) for each model to see
|
||||||
what is supported.
|
what is supported.
|
||||||
base_url: Base API URL for the Hathora TTS service.
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
speed: Optional[float] = None
|
speed: Optional[float] = None
|
||||||
config: Optional[list[ConfigOption]] = None
|
config: Optional[list[ConfigOption]] = None
|
||||||
base_url: str = "https://api.models.hathora.dev/inference/v1/tts",
|
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
*,
|
*,
|
||||||
model: str,
|
model: str,
|
||||||
voice_id: Optional[str] = None,
|
voice_id: Optional[str] = None,
|
||||||
|
sample_rate: Optional[int] = None,
|
||||||
api_key: Optional[str] = None,
|
api_key: Optional[str] = None,
|
||||||
|
base_url: str = "https://api.models.hathora.dev/inference/v1/tts",
|
||||||
params: Optional[InputParams] = None,
|
params: Optional[InputParams] = None,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
):
|
):
|
||||||
@@ -81,17 +81,20 @@ class HathoraTTSService(TTSService):
|
|||||||
model: Model to use; find available models
|
model: Model to use; find available models
|
||||||
[here](https://models.hathora.dev).
|
[here](https://models.hathora.dev).
|
||||||
voice_id: Voice to use for synthesis (if supported by model).
|
voice_id: Voice to use for synthesis (if supported by model).
|
||||||
|
sample_rate: Output sample rate for generated audio.
|
||||||
api_key: API key for authentication with the Hathora service;
|
api_key: API key for authentication with the Hathora service;
|
||||||
provision one [here](https://models.hathora.dev/tokens).
|
provision one [here](https://models.hathora.dev/tokens).
|
||||||
|
base_url: Base API URL for the Hathora TTS service.
|
||||||
params: Configuration parameters.
|
params: Configuration parameters.
|
||||||
**kwargs: Additional arguments passed to the parent class.
|
**kwargs: Additional arguments passed to the parent class.
|
||||||
"""
|
"""
|
||||||
super().__init__(
|
super().__init__(
|
||||||
|
sample_rate=sample_rate,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
)
|
)
|
||||||
self._model = model
|
self._model = model
|
||||||
self._api_key = api_key or os.getenv("HATHORA_API_KEY")
|
self._api_key = api_key or os.getenv("HATHORA_API_KEY")
|
||||||
self._base_url = params.base_url
|
self._base_url = base_url
|
||||||
|
|
||||||
params = params or HathoraTTSService.InputParams()
|
params = params or HathoraTTSService.InputParams()
|
||||||
|
|
||||||
@@ -155,7 +158,7 @@ class HathoraTTSService(TTSService):
|
|||||||
|
|
||||||
frame = TTSAudioRawFrame(
|
frame = TTSAudioRawFrame(
|
||||||
audio=pcm_audio,
|
audio=pcm_audio,
|
||||||
sample_rate=sample_rate,
|
sample_rate=self.sample_rate,
|
||||||
num_channels=num_channels,
|
num_channels=num_channels,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user