wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2020 from snova-jorgep/snova-jorgep/sambanova-integration

Browse Source 
Add Sambanova LLM and STT integration
This commit is contained in:
Mark Backman
2025-06-24 17:04:24 -04:00
committed by GitHub
parent f450da57e5 851cf079c3
commit 3eed316049
10 changed files with 530 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
CHANGELOG.md
View File

@@ -52,6 +52,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
`LLMAssistantContextAggregator` that exposes whether a function call is in
progress.
- Added `SambaNovaLLMService` which provides llm api integration with an
OpenAI-compatible interface.
- Added `SambaNovaTTSService` which provides speech-to-text functionality using
SambaNovas's (whisper) API.
- Add fundational examples for function calling and transcription
`14s-function-calling-sambanova.py`, `13g-sambanova-transcription.py`
### Changed
- `HeartbeatFrame`s are now control frames. This will make it easier to detect

4
README.md
View File

@@ -53,8 +53,8 @@ You can connect to Pipecat from any platform using our official SDKs:
| Category | Services |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova) [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
| Text-to-Speech | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) |
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |

1
docs/api/requirements.txt
View File

@@ -42,6 +42,7 @@ pipecat-ai[openai]
pipecat-ai[qwen]
pipecat-ai[remote-smart-turn]
# pipecat-ai[riva] # Mocked
pipecat-ai[sambanova]
pipecat-ai[silero]
pipecat-ai[simli]
pipecat-ai[soundfile]

5
dot-env.template
View File

@@ -109,5 +109,8 @@ MINIMAX_GROUP_ID=...
# Sarvam AI
SARVAM_API_KEY=...
# SambaNova
SAMBANOVA_API_KEY=...
# Sentry
SENTRY_DSN=...
SENTRY_DSN=...

108
examples/foundational/13g-sambanova-transcription.py Normal file
View File

@@ -0,0 +1,108 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import time
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeakingFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
STOP_SECS = 2.0
class TranscriptionLogger(FrameProcessor):
"""Measures transcription latency.
Uses the (intentionally) long STOP_SECS parameter to give the transcription time to finish,
then outputs the timing between when the VAD first classified audio input as not-speech and
the delivery of the last transcription frame.
"""
def __init__(self):
super().__init__()
self._last_transcription_time = time.time()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, UserStoppedSpeakingFrame):
logger.debug(
f"Transcription latency: {(STOP_SECS - (time.time() - self._last_transcription_time)):.2f}"
)
if isinstance(frame, TranscriptionFrame):
self._last_transcription_time = time.time()
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

152
examples/foundational/14s-function-calling-sambanova.py Normal file
View File

@@ -0,0 +1,152 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.sambanova.llm import SambaNovaLLMService
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
await params.result_callback({"conditions": "nice", "temperature": "75"})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = SambaNovaLLMService(
api_key=os.getenv("SAMBANOVA_API_KEY"),
model="Llama-4-Maverick-17B-128E-Instruct",
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("get_current_weather", fetch_weather_from_api)
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location"],
)
tools = ToolsSchema(standard_tools=[weather_function])
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

1
pyproject.toml
View File

@@ -79,6 +79,7 @@ playht = [ "pyht~=0.1.12", "websockets~=13.1" ]
qwen = []
rime = [ "websockets~=13.1" ]
riva = [ "nvidia-riva-client~=2.19.1" ]
sambanova = []
sentry = [ "sentry-sdk~=2.23.1" ]
local-smart-turn = [ "coremltools>=8.0", "transformers", "torch==2.5.0", "torchaudio==2.5.0" ]
remote-smart-turn = []

8
src/pipecat/services/sambanova/__init__.py Normal file
View File

@@ -0,0 +1,8 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from .llm import *
from .stt import *

180
src/pipecat/services/sambanova/llm.py Normal file
View File

@@ -0,0 +1,180 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import json
from typing import Any, Dict, List, Optional
from loguru import logger
from openai import AsyncStream
from openai.types.chat import ChatCompletionChunk, ChatCompletionMessageParam
from pipecat.frames.frames import (
LLMTextFrame,
)
from pipecat.metrics.metrics import LLMTokenUsage
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.llm_service import FunctionCallFromLLM
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.utils.tracing.service_decorators import traced_llm
class SambaNovaLLMService(OpenAILLMService): # type: ignore
"""A service for interacting with SambaNova using the OpenAI-compatible interface.
This service extends OpenAILLMService to connect to SambaNova's API endpoint while
maintaining full compatibility with OpenAI's interface and functionality.
Args:
api_key (str): The API key for accessing SambaNova API.
model (str, optional): The model identifier to use. Defaults to "Meta-Llama-3.3-70B-Instruct".
base_url (str, optional): The base URL for SambaNova API. Defaults to "https://api.sambanova.ai/v1".
**kwargs: Additional keyword arguments passed to OpenAILLMService.
"""
def __init__(
self,
*,
api_key: str,
model: str = "Llama-4-Maverick-17B-128E-Instruct",
base_url: str = "https://api.sambanova.ai/v1",
**kwargs: Dict[Any, Any],
) -> None:
super().__init__(api_key=api_key, base_url=base_url, model=model, **kwargs)
def create_client(
self,
api_key: Optional[str] = None,
base_url: Optional[str] = None,
**kwargs: Dict[Any, Any],
) -> Any:
"""Create OpenAI-compatible client for SambaNova API endpoint."""
logger.debug(f"Creating SambaNova client with API {base_url}")
return super().create_client(api_key, base_url, **kwargs)
async def get_chat_completions(
self, context: OpenAILLMContext, messages: List[ChatCompletionMessageParam]
) -> Any:
"""Get chat completions from SambaNova API endpoint."""
params = {
"model": self.model_name,
"stream": True,
"messages": messages,
"tools": context.tools,
"tool_choice": context.tool_choice,
"stream_options": {"include_usage": True},
"temperature": self._settings["temperature"],
"top_p": self._settings["top_p"],
"max_tokens": self._settings["max_tokens"],
"max_completion_tokens": self._settings["max_completion_tokens"],
}
params.update(self._settings["extra"])
chunks = await self._client.chat.completions.create(**params)
return chunks
@traced_llm # type: ignore
async def _process_context(self, context: OpenAILLMContext) -> AsyncStream[ChatCompletionChunk]:
"""Redefine this method until SambaNova API introduces indexing in tool calls."""
functions_list = []
arguments_list = []
tool_id_list = []
func_idx = 0
function_name = ""
arguments = ""
tool_call_id = ""
await self.start_ttfb_metrics()
chunk_stream: AsyncStream[ChatCompletionChunk] = await self._stream_chat_completions(
context
)
async for chunk in chunk_stream:
if chunk.usage:
tokens = LLMTokenUsage(
prompt_tokens=chunk.usage.prompt_tokens,
completion_tokens=chunk.usage.completion_tokens,
total_tokens=chunk.usage.total_tokens,
)
await self.start_llm_usage_metrics(tokens)
if chunk.choices is None or len(chunk.choices) == 0:
continue
await self.stop_ttfb_metrics()
if not chunk.choices[0].delta:
continue
if chunk.choices[0].delta.tool_calls:
# We're streaming the LLM response to enable the fastest response times.
# For text, we just yield each chunk as we receive it and count on consumers
# to do whatever coalescing they need (eg. to pass full sentences to TTS)
#
# If the LLM is a function call, we'll do some coalescing here.
# If the response contains a function name, we'll yield a frame to tell consumers
# that they can start preparing to call the function with that name.
# We accumulate all the arguments for the rest of the streamed response, then when
# the response is done, we package up all the arguments and the function name and
# yield a frame containing the function name and the arguments.
tool_call = chunk.choices[0].delta.tool_calls[0]
if tool_call.index != func_idx:
functions_list.append(function_name)
arguments_list.append(arguments)
tool_id_list.append(tool_call_id)
function_name = ""
arguments = ""
tool_call_id = ""
func_idx += 1
if tool_call.function and tool_call.function.name:
function_name += tool_call.function.name
tool_call_id = tool_call.id # type: ignore
if tool_call.function and tool_call.function.arguments:
# Keep iterating through the response to collect all the argument fragments
arguments += tool_call.function.arguments
elif chunk.choices[0].delta.content:
await self.push_frame(LLMTextFrame(chunk.choices[0].delta.content))
# When gpt-4o-audio / gpt-4o-mini-audio is used for llm or stt+llm
# we need to get LLMTextFrame for the transcript
elif hasattr(chunk.choices[0].delta, "audio") and chunk.choices[0].delta.audio.get(
"transcript"
):
await self.push_frame(LLMTextFrame(chunk.choices[0].delta.audio["transcript"]))
# if we got a function name and arguments, check to see if it's a function with
# a registered handler. If so, run the registered callback, save the result to
# the context, and re-prompt to get a chat answer. If we don't have a registered
# handler, raise an exception.
if function_name and arguments:
# added to the list as last function name and arguments not added to the list
functions_list.append(function_name)
arguments_list.append(arguments)
tool_id_list.append(tool_call_id)
function_calls = []
for function_name, arguments, tool_id in zip(
functions_list, arguments_list, tool_id_list
):
# This allows compatibility until SambaNova API introduces indexing in tool calls.
if len(arguments) < 1:
continue
arguments = json.loads(arguments)
function_calls.append(
FunctionCallFromLLM(
context=context,
tool_call_id=tool_id,
function_name=function_name,
arguments=arguments,
)
)
await self.run_function_calls(function_calls)

65
src/pipecat/services/sambanova/stt.py Normal file
View File

@@ -0,0 +1,65 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from typing import Any, Optional
from pipecat.services.whisper.base_stt import BaseWhisperSTTService, Transcription
from pipecat.transcriptions.language import Language
class SambaNovaSTTService(BaseWhisperSTTService): # type: ignore
"""SambaNova Whisper speech-to-text service.
Uses SambaNova's Whisper API to convert audio to text.
Requires a SambaNova API key set via the api_key parameter or SAMBANOVA_API_KEY environment variable.
Args:
model: Whisper model to use. Defaults to "Whisper-Large-v3".
api_key: SambaNova API key. Defaults to None.
base_url: API base URL. Defaults to "https://api.sambanova.ai/v1".
language: Language of the audio input. Defaults to English.
prompt: Optional text to guide the model's style or continue a previous segment.
temperature: Optional sampling temperature between 0 and 1. Defaults to 0.0.
**kwargs: Additional arguments passed to `pipecat.services.whisper.base_stt.BaseWhisperSTTService`.
"""
def __init__(
self,
*,
model: str = "Whisper-Large-v3",
api_key: Optional[str] = None,
base_url: str = "https://api.sambanova.ai/v1",
language: Optional[Language] = Language.EN,
prompt: Optional[str] = None,
temperature: Optional[float] = None,
**kwargs: Any,
) -> None:
super().__init__(
model=model,
api_key=api_key,
base_url=base_url,
language=language,
prompt=prompt,
temperature=temperature,
**kwargs,
)
async def _transcribe(self, audio: bytes) -> Transcription:
assert self._language is not None # Assigned in the BaseWhisperSTTService class
# Build kwargs dict with only set parameters
kwargs = {
"file": ("audio.wav", audio, "audio/wav"),
"model": self.model_name,
"response_format": "json",
"language": self._language,
}
if self._prompt is not None:
kwargs["prompt"] = self._prompt
if self._temperature is not None:
kwargs["temperature"] = self._temperature
return await self._client.audio.transcriptions.create(**kwargs)