Spaces:
Runtime error
Runtime error
File size: 8,134 Bytes
ed4d993 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
from __future__ import annotations
from enum import Enum
from pathlib import Path
from typing import TYPE_CHECKING, Iterator, Optional, Union
import requests
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
if TYPE_CHECKING:
import assemblyai
class TranscriptFormat(Enum):
"""Transcript format to use for the document loader."""
TEXT = "text"
"""One document with the transcription text"""
SENTENCES = "sentences"
"""Multiple documents, splits the transcription by each sentence"""
PARAGRAPHS = "paragraphs"
"""Multiple documents, splits the transcription by each paragraph"""
SUBTITLES_SRT = "subtitles_srt"
"""One document with the transcript exported in SRT subtitles format"""
SUBTITLES_VTT = "subtitles_vtt"
"""One document with the transcript exported in VTT subtitles format"""
class AssemblyAIAudioTranscriptLoader(BaseLoader):
"""Load AssemblyAI audio transcripts.
It uses the AssemblyAI API to transcribe audio files
and loads the transcribed text into one or more Documents,
depending on the specified format.
To use, you should have the ``assemblyai`` python package installed, and the
environment variable ``ASSEMBLYAI_API_KEY`` set with your API key.
Alternatively, the API key can also be passed as an argument.
Audio files can be specified via an URL or a local file path.
"""
def __init__(
self,
file_path: Union[str, Path],
*,
transcript_format: TranscriptFormat = TranscriptFormat.TEXT,
config: Optional[assemblyai.TranscriptionConfig] = None,
api_key: Optional[str] = None,
):
"""
Initializes the AssemblyAI AudioTranscriptLoader.
Args:
file_path: An URL or a local file path.
transcript_format: Transcript format to use.
See class ``TranscriptFormat`` for more info.
config: Transcription options and features. If ``None`` is given,
the Transcriber's default configuration will be used.
api_key: AssemblyAI API key.
"""
try:
import assemblyai
except ImportError:
raise ImportError(
"Could not import assemblyai python package. "
"Please install it with `pip install assemblyai`."
)
if api_key is not None:
assemblyai.settings.api_key = api_key
self.file_path = str(file_path)
self.transcript_format = transcript_format
self.transcriber = assemblyai.Transcriber(config=config)
def lazy_load(self) -> Iterator[Document]:
"""Transcribes the audio file and loads the transcript into documents.
It uses the AssemblyAI API to transcribe the audio file and blocks until
the transcription is finished.
"""
transcript = self.transcriber.transcribe(self.file_path)
# This will raise a ValueError if no API key is set.
if transcript.error:
raise ValueError(f"Could not transcribe file: {transcript.error}")
if self.transcript_format == TranscriptFormat.TEXT:
yield Document(
page_content=transcript.text, metadata=transcript.json_response
)
elif self.transcript_format == TranscriptFormat.SENTENCES:
sentences = transcript.get_sentences()
for s in sentences:
yield Document(page_content=s.text, metadata=s.dict(exclude={"text"}))
elif self.transcript_format == TranscriptFormat.PARAGRAPHS:
paragraphs = transcript.get_paragraphs()
for p in paragraphs:
yield Document(page_content=p.text, metadata=p.dict(exclude={"text"}))
elif self.transcript_format == TranscriptFormat.SUBTITLES_SRT:
yield Document(page_content=transcript.export_subtitles_srt())
elif self.transcript_format == TranscriptFormat.SUBTITLES_VTT:
yield Document(page_content=transcript.export_subtitles_vtt())
else:
raise ValueError("Unknown transcript format.")
class AssemblyAIAudioLoaderById(BaseLoader):
"""
Load AssemblyAI audio transcripts.
It uses the AssemblyAI API to get an existing transcription
and loads the transcribed text into one or more Documents,
depending on the specified format.
"""
def __init__(
self, transcript_id: str, api_key: str, transcript_format: TranscriptFormat
):
"""
Initializes the AssemblyAI AssemblyAIAudioLoaderById.
Args:
transcript_id: Id of an existing transcription.
transcript_format: Transcript format to use.
See class ``TranscriptFormat`` for more info.
api_key: AssemblyAI API key.
"""
self.api_key = api_key
self.transcript_id = transcript_id
self.transcript_format = transcript_format
def lazy_load(self) -> Iterator[Document]:
"""Load data into Document objects."""
HEADERS = {"authorization": self.api_key}
if self.transcript_format == TranscriptFormat.TEXT:
try:
transcript_response = requests.get(
f"https://api.assemblyai.com/v2/transcript/{self.transcript_id}",
headers=HEADERS,
)
transcript_response.raise_for_status()
except Exception as e:
print(f"An error occurred: {e}") # noqa: T201
raise
transcript = transcript_response.json()["text"]
yield Document(page_content=transcript, metadata=transcript_response.json())
elif self.transcript_format == TranscriptFormat.PARAGRAPHS:
try:
paragraphs_response = requests.get(
f"https://api.assemblyai.com/v2/transcript/{self.transcript_id}/paragraphs",
headers=HEADERS,
)
paragraphs_response.raise_for_status()
except Exception as e:
print(f"An error occurred: {e}") # noqa: T201
raise
paragraphs = paragraphs_response.json()["paragraphs"]
for p in paragraphs:
yield Document(page_content=p["text"], metadata=p)
elif self.transcript_format == TranscriptFormat.SENTENCES:
try:
sentences_response = requests.get(
f"https://api.assemblyai.com/v2/transcript/{self.transcript_id}/sentences",
headers=HEADERS,
)
sentences_response.raise_for_status()
except Exception as e:
print(f"An error occurred: {e}") # noqa: T201
raise
sentences = sentences_response.json()["sentences"]
for s in sentences:
yield Document(page_content=s["text"], metadata=s)
elif self.transcript_format == TranscriptFormat.SUBTITLES_SRT:
try:
srt_response = requests.get(
f"https://api.assemblyai.com/v2/transcript/{self.transcript_id}/srt",
headers=HEADERS,
)
srt_response.raise_for_status()
except Exception as e:
print(f"An error occurred: {e}") # noqa: T201
raise
srt = srt_response.text
yield Document(page_content=srt)
elif self.transcript_format == TranscriptFormat.SUBTITLES_VTT:
try:
vtt_response = requests.get(
f"https://api.assemblyai.com/v2/transcript/{self.transcript_id}/vtt",
headers=HEADERS,
)
vtt_response.raise_for_status()
except Exception as e:
print(f"An error occurred: {e}") # noqa: T201
raise
vtt = vtt_response.text
yield Document(page_content=vtt)
else:
raise ValueError("Unknown transcript format.")
|