Skip to content

Sunset saaras and saarika v2.5 #6905

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dhruvladia-sarvam wants to merge 1 commit into
base: main
Choose a base branch
from
+5 −47
Open

Sunset saaras and saarika v2.5 #6905

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 5 additions & 47 deletions livekit-plugins/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,18 +62,15 @@
SARVAM_STT_TRANSLATE_STREAMING_URL = "wss://api.sarvam.ai/speech-to-text-translate/ws"

# Models
SarvamSTTModels = Literal["saarika:v2.5", "saaras:v2.5", "saaras:v3"]
SarvamSTTModels = Literal["saaras:v3"]
SarvamSTTModes = Literal["transcribe", "translate", "verbatim", "translit", "codemix"]

# Valid mode values (single source of truth)
ALLOWED_MODES: set[str] = {"transcribe", "translate", "verbatim", "translit", "codemix"}


class SpeechToTextLanguage(str, Enum):
"""Languages supported for STT.

saarika:v2.5 supports only a subset; saaras:v3 supports all.
"""
"""Languages supported for STT."""

UNKNOWN = "unknown"
HI_IN = "hi-IN"
Expand All @@ -87,7 +84,6 @@ class SpeechToTextLanguage(str, Enum):
TE_IN = "te-IN"
EN_IN = "en-IN"
GU_IN = "gu-IN"
# saaras:v3-only languages (saarika:v2.5 raises error if requested)
ASSAMESE = "as-IN"
URDU = "ur-IN"
NEPALI = "ne-IN"
Expand All @@ -103,20 +99,6 @@ class SpeechToTextLanguage(str, Enum):


SAARAS_V3_LANGUAGES = {lang.value for lang in SpeechToTextLanguage}
SAARIKA_V25_LANGUAGES: set[str] = {
SpeechToTextLanguage.UNKNOWN.value,
SpeechToTextLanguage.HI_IN.value,
SpeechToTextLanguage.BN_IN.value,
SpeechToTextLanguage.KN_IN.value,
SpeechToTextLanguage.ML_IN.value,
SpeechToTextLanguage.MR_IN.value,
SpeechToTextLanguage.OD_IN.value,
SpeechToTextLanguage.PA_IN.value,
SpeechToTextLanguage.TA_IN.value,
SpeechToTextLanguage.TE_IN.value,
SpeechToTextLanguage.EN_IN.value,
SpeechToTextLanguage.GU_IN.value,
}


@dataclass(frozen=True)
Expand Down Expand Up @@ -147,28 +129,6 @@ class ModelConfig:


MODEL_CONFIGS: dict[str, ModelConfig] = {
"saarika:v2.5": ModelConfig(
supports_prompt=False,
supports_mode=False,
supports_language=True,
supports_vad_params=False,
default_language="unknown",
default_mode=None,
use_translate_endpoint=False,
use_translate_method=False,
allowed_languages=SAARIKA_V25_LANGUAGES,
),
"saaras:v2.5": ModelConfig(
supports_prompt=True,
supports_mode=False,
supports_language=False,
supports_vad_params=False,
default_language=None,
default_mode=None,
use_translate_endpoint=True,
use_translate_method=True,
allowed_languages=SAARIKA_V25_LANGUAGES,
),
"saaras:v3": ModelConfig(
supports_prompt=False,
supports_mode=True,
Expand Down Expand Up @@ -294,7 +254,7 @@ class SarvamSTTOptions:

language: str # BCP-47 language code, e.g., "hi-IN", "en-IN"
api_key: str
model: SarvamSTTModels | str = "saarika:v2.5"
model: SarvamSTTModels | str = "saaras:v3"
mode: SarvamSTTModes | str = "transcribe"
base_url: str | None = None
streaming_url: str | None = None
Expand Down Expand Up @@ -489,7 +449,7 @@ def __init__(
self,
*,
language: str = "en-IN",
model: SarvamSTTModels | str = "saarika:v2.5",
model: SarvamSTTModels | str = "saaras:v3",
mode: SarvamSTTModes | str = "transcribe",
api_key: str | None = None,
base_url: str | None = None,
Expand Down Expand Up @@ -656,9 +616,7 @@ async def _recognize_impl(
form_data = aiohttp.FormData()
form_data.add_field("file", wav_bytes, filename="audio.wav", content_type="audio/wav")

# Add model and language_code to the form data if specified
# Sarvam API docs state language_code is optional for saarika:v2x but mandatory for v1
# Model is also optional, defaults to saarika:v2.5
# Add model and language_code to the form data
if opts_language:
form_data.add_field("language_code", opts_language)
if opts_model:
Expand Down