Compare commits

...
19 Commits
Author SHA1 Message Date
Barabazs 9de90e2664 fix: pin huggingface-hub<1.0.0 for pyannote-audio compatibility (#1327)
* fix: pin huggingface-hub<1.0.0 for pyannote-audio compatibility

pyannote-audio uses the deprecated `use_auth_token` parameter which was removed in huggingface-hub v1.0.0

* fix: upgrade yanked dependencies

* chore: update version to 3.7.5
2026-01-27 09:45:05 +01:00
Barabazs d32ec3e301 fix: add missing comma 2025-10-21 09:13:50 -06:00
db317c358b feat: add language-aware sentence tokenization (#1269)
* feat: add language-aware sentence tokenization

* feat: add missing punkt languages

---------

Co-authored-by: pulkit <129310466+p1kit@users.noreply.github.com>
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
2025-10-21 15:57:26 +02:00
JulianFP 6e1d1caaf4 fix: incorrect type annotation in get_writer return value
The audio_path attribute that the __call__ method of the ResultWriter class takes is a str, not TextIO
2025-10-17 09:43:43 -06:00
Barabazs c8f7597345 feat: add hotwords argument to CLI for improved recognition of rare terms 2025-10-17 09:21:56 -06:00
Barabazs 5925e5f8c7 docs: add cuDNN troubleshooting for common issues (#1266)
* docs: add troubleshooting guide for cuDNN loading errors

* docs: add cuDNN version incompatibility troubleshooting
2025-10-16 10:56:51 +02:00
Barabazs 617835dc27 chore: upgrade torch and torchaudio dependencies to 2.8.0 2025-10-16 07:41:45 +00:00
Barabazs 92227e7412 fix: lock down torch and torchaudio versions (#1265)
* fix: update torch and torchaudio dependencies to use compatible version specifiers

* chore: update version to 3.7.3
2025-10-16 08:42:10 +02:00
PaffeandPaffe 0fa81b31f1 feat: add Swedish alignment model (#1110)
---------

Co-authored-by: Paffe <paffe@Sigge.home>
2025-10-15 08:08:18 +02:00
Barabazs 505bd9c0b5 chore: refine triton dependency to restrict installation to x86_64 Linux (#1259)
* chore: refine triton dependency to restrict installation to x86_64 Linux

* bump: update version to 3.7.2
2025-10-12 10:38:29 +02:00
Barabazs 895e5a8493 chore: update numpy dependency constraints for Python 3.13 compatibility (#1258)
* chore: update numpy dependency constraints for Python 3.13 compatibility

* bump: update version to 3.7.1
2025-10-12 10:31:44 +02:00
Barabazs a58ff9cb20 bump: update version to 3.7.0 2025-10-10 07:37:17 +00:00
Barabazs d13171cdde feat: add support for python 3.13 (#1256)
* feat: update Python version requirement to be compatible with 3.13

* feat: add Python 3.13 to compatibility matrix

* feat: update onnxruntime dependency for Python version compatibility

* fix: drop onnxruntime restriction for python >= 3.10
2025-10-10 09:36:24 +02:00
Barabazs c1c08c472f bump: update version to 3.6.0 2025-10-10 06:45:00 +00:00
Barabazs a51ae7a81a feat: add centralized logging to replace ad-hoc print statements (#1254)
* feat: add logging utility functions

* feat: add logging setup and log level argument to CLI

* feat: integrate logging across modules
2025-10-10 08:41:06 +02:00
Barabazs 3b1b9a8c4d refactor: rename types.py to schema.py to avoid stdlib conflict 2025-10-09 14:25:58 +02:00
Tomáš Hnyk 027ec57aee doc: update cpu only example (#1164) 2025-10-09 09:34:54 +02:00
3manifold 64e307cc29 chore: remove redundant variable & improve load_model function documentation (#1197)
* Remove redundant variable

* Improve function documentation
2025-10-09 09:32:02 +02:00
Adrian Wan 2663f2edb5 doc: fix diarize import in example script (#1192) 2025-10-09 09:27:07 +02:00
16 changed files with 1214 additions and 206 deletions

No files matched your search

+1 -1
View File
@@ -12,7 +12,7 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.9", "3.10", "3.11", "3.12"]
python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
steps:
- uses: actions/checkout@v4
+76
View File
@@ -0,0 +1,76 @@
# Troubleshooting cuDNN Loading Errors
This guide helps resolve common cuDNN-related errors when running WhisperX on GPU. These issues typically occur when the system can't locate cuDNN libraries or finds conflicting versions.
## Unable to Load cuDNN Libraries
If you encounter the following error when running WhisperX:
`Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}`
This means the cuDNN libraries are installed (via whisperx dependencies) but aren't in a location where the system's dynamic linker can find them.
### Solution 1: Add to LD_LIBRARY_PATH (Recommended)
Add this at the start of your Python script or notebook:
```python
import os
# Get current LD_LIBRARY_PATH
original = os.environ.get("LD_LIBRARY_PATH", "")
cudnn_path = "/usr/local/lib/python3.12/dist-packages/nvidia/cudnn/lib/"
os.environ['LD_LIBRARY_PATH'] = original + ":" + cudnn_path
```
**Note:** Adjust the Python version (`python3.12`) to match your environment.
### Solution 2: Symlink to LD_LIBRARY_PATH Directory
If Solution 1 didn't work and you still get the "unable to load" error, symlink the libraries to a directory that's already in your `LD_LIBRARY_PATH`:
1. Check what's in your LD_LIBRARY_PATH: `echo "$LD_LIBRARY_PATH"`
2. Assuming that there is only one path set.
Symlink the downloaded libcudnn files to that path:
`ln -s /usr/local/lib/python3.12/dist-packages/nvidia/cudnn/lib/libcudnn* "$LD_LIBRARY_PATH"/`
**Note:** If `LD_LIBRARY_PATH` contains multiple paths (separated by `:`), pick one directory and use it instead of `"$LD_LIBRARY_PATH"`. For example: `/usr/lib/x86_64-linux-gnu/`
## cuDNN Version Incompatibility
If you encounter this error:
```
RuntimeError: cuDNN version incompatibility: PyTorch was compiled against (9, 10, 2) but found runtime version (9, 2, 1)
```
This means PyTorch is finding a different cuDNN version than the one it was compiled with. **PyTorch comes bundled with its own cuDNN**, but a conflicting cuDNN in `LD_LIBRARY_PATH` is taking precedence.
### Solution: Remove Conflicting cuDNN from Path
Check if there's a conflicting cuDNN path:
```bash
echo $LD_LIBRARY_PATH
```
If you see paths pointing to older cuDNN installations (e.g., system-installed cuDNN or manually downloaded), try one of these:
**Option 1: Clear LD_LIBRARY_PATH temporarily**
```python
import os
# Let PyTorch use its bundled cuDNN
os.environ.pop('LD_LIBRARY_PATH', None)
```
**Option 2: Set LD_LIBRARY_PATH to only the correct version**
```python
import os
# Point only to the cuDNN that matches PyTorch's compiled version
os.environ['LD_LIBRARY_PATH'] = "/usr/local/lib/python3.12/dist-packages/nvidia/cudnn/lib/"
```
**Note:** This error is unlikely on a clean install. If it occurs anyway, [open an issue](https://github.com/m-bain/whisperX/issues). If you've modified system libraries or CUDA/cuDNN, the options above should help resolve most cases.
+3 -2
View File
@@ -144,7 +144,7 @@ To label the transcript with speaker ID's (set number of speakers if known e.g.
To run on CPU instead of GPU (and for running on Mac OS X):
whisperx path/to/audio.wav --compute_type int8
whisperx path/to/audio.wav --compute_type int8 --device cpu
### Other languages
@@ -166,6 +166,7 @@ See more examples in other languages [here](EXAMPLES.md).
```python
import whisperx
import gc
from whisperx.diarize import DiarizationPipeline
device = "cuda"
audio_file = "audio.mp3"
@@ -196,7 +197,7 @@ print(result["segments"]) # after alignment
# import gc; import torch; gc.collect(); torch.cuda.empty_cache(); del model_a
# 3. Assign speaker labels
diarize_model = whisperx.diarize.DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
diarize_model = DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
# add min/max number of speakers if known
diarize_segments = diarize_model(audio)
+9 -7
View File
@@ -2,10 +2,10 @@
urls = { repository = "https://github.com/m-bain/whisperx" }
authors = [{ name = "Max Bain" }]
name = "whisperx"
version = "3.5.0"
version = "3.7.5"
description = "Time-Accurate Automatic Speech Recognition using Whisper."
readme = "README.md"
requires-python = ">=3.9, <3.13"
requires-python = ">=3.9, <3.14"
license = { text = "BSD-2-Clause" }
dependencies = [
@@ -13,15 +13,17 @@ dependencies = [
"faster-whisper>=1.1.1",
"nltk>=3.9.1",
# Restrict numpy, onnxruntime, pandas, av to be compatible with Python 3.9
"numpy>=2.0.2,<2.1.0",
"onnxruntime>=1.19,<1.20.0",
"numpy>=2.0.2,<2.1.0; python_version <'3.13'",
"onnxruntime>=1.19,<1.20.0; python_version <'3.10'",
"pandas>=2.2.3,<2.3.0",
"av<16.0.0",
"numpy>=2.1.0,<2.3.0; python_version >='3.13'",
"pyannote-audio>=3.3.2,<4.0.0",
"torch>=2.7.1",
"torchaudio",
"huggingface-hub<1.0.0",
"torch~=2.8.0",
"torchaudio~=2.8.0",
"transformers>=4.48.0",
"triton>=3.3.0; sys_platform == 'linux'" # only install triton on Linux
"triton>=3.3.0; sys_platform == 'linux' and platform_machine == 'x86_64'" # only install triton on x86_64 Linux
]
Generated
+941 -165
View File
File diff suppressed because it is too large. Load diff
+26
View File
@@ -29,3 +29,29 @@ def load_audio(*args, **kwargs):
def assign_word_speakers(*args, **kwargs):
diarize = _lazy_import("diarize")
return diarize.assign_word_speakers(*args, **kwargs)
def setup_logging(*args, **kwargs):
"""
Configure logging for WhisperX.
Args:
level: Logging level (debug, info, warning, error, critical). Default: warning
log_file: Optional path to log file. If None, logs only to console.
"""
logging_module = _lazy_import("log_utils")
return logging_module.setup_logging(*args, **kwargs)
def get_logger(*args, **kwargs):
"""
Get a logger instance for the given module.
Args:
name: Logger name (typically __name__ from calling module)
Returns:
Logger instance configured with WhisperX settings
"""
logging_module = _lazy_import("log_utils")
return logging_module.get_logger(*args, **kwargs)
+13
View File
@@ -6,6 +6,7 @@ import torch
from whisperx.utils import (LANGUAGES, TO_LANGUAGE_CODE, optional_float,
optional_int, str2bool)
from whisperx.log_utils import setup_logging
def cli():
@@ -23,6 +24,7 @@ def cli():
parser.add_argument("--output_dir", "-o", type=str, default=".", help="directory to save the outputs")
parser.add_argument("--output_format", "-f", type=str, default="all", choices=["all", "srt", "vtt", "txt", "tsv", "json", "aud"], help="format of the output file; if not specified, all available formats will be produced")
parser.add_argument("--verbose", type=str2bool, default=True, help="whether to print out the progress and debug messages")
parser.add_argument("--log-level", type=str, default=None, choices=["debug", "info", "warning", "error", "critical"], help="logging level (overrides --verbose if set)")
parser.add_argument("--task", type=str, default="transcribe", choices=["transcribe", "translate"], help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')")
parser.add_argument("--language", type=str, default=None, choices=sorted(LANGUAGES.keys()) + sorted([k.title() for k in TO_LANGUAGE_CODE.keys()]), help="language spoken in the audio, specify None to perform language detection")
@@ -56,6 +58,7 @@ def cli():
parser.add_argument("--suppress_numerals", action="store_true", help="whether to suppress numeric symbols and currency symbols during sampling, since wav2vec2 cannot align them correctly")
parser.add_argument("--initial_prompt", type=str, default=None, help="optional text to provide as a prompt for the first window.")
parser.add_argument("--hotwords", type=str, default=None, help="hotwords/hint phrases to the model (e.g. \"WhisperX, PyAnnote, GPU\"); improves recognition of rare/technical terms")
parser.add_argument("--condition_on_previous_text", type=str2bool, default=False, help="if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop")
parser.add_argument("--fp16", type=str2bool, default=True, help="whether to perform inference in fp16; True by default")
@@ -80,6 +83,16 @@ def cli():
args = parser.parse_args().__dict__
log_level = args.get("log_level")
verbose = args.get("verbose")
if log_level is not None:
setup_logging(level=log_level)
elif verbose:
setup_logging(level="info")
else:
setup_logging(level="warning")
from whisperx.transcribe import transcribe_task
transcribe_task(args, parser)
+16 -9
View File
@@ -14,8 +14,8 @@ import torchaudio
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
from whisperx.audio import SAMPLE_RATE, load_audio
from whisperx.utils import interpolate_nans
from whisperx.types import (
from whisperx.utils import interpolate_nans, PUNKT_LANGUAGES
from whisperx.schema import (
AlignedTranscriptionResult,
SingleSegment,
SingleAlignedSegment,
@@ -24,6 +24,9 @@ from whisperx.types import (
)
import nltk
from nltk.data import load as nltk_load
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
LANGUAGES_WITHOUT_SPACES = ["ja", "zh"]
@@ -70,6 +73,7 @@ DEFAULT_ALIGN_MODELS_HF = {
"ka": "xsway/wav2vec2-large-xlsr-georgian",
"lv": "jimregan/wav2vec2-large-xlsr-latvian-cv",
"tl": "Khalsuu/filipino-wav2vec2-l-xls-r-300m-official",
"sv": "KBLab/wav2vec2-large-voxrex-swedish",
}
@@ -81,8 +85,9 @@ def load_align_model(language_code: str, device: str, model_name: Optional[str]
elif language_code in DEFAULT_ALIGN_MODELS_HF:
model_name = DEFAULT_ALIGN_MODELS_HF[language_code]
else:
print(f"There is no default alignment model set for this language ({language_code}).\
Please find a wav2vec2.0 model finetuned on this language in https://huggingface.co/models, then pass the model name in --align_model [MODEL_NAME]")
logger.error(f"No default alignment model for language: {language_code}. "
f"Please find a wav2vec2.0 model finetuned on this language at https://huggingface.co/models, "
f"then pass the model name via --align_model [MODEL_NAME]")
raise ValueError(f"No default align-model for language: {language_code}")
if model_name in torchaudio.pipelines.__all__:
@@ -187,11 +192,13 @@ def align(
clean_wdx.append(wdx)
# Use language-specific Punkt model if available otherwise we fallback to English.
punkt_lang = PUNKT_LANGUAGES.get(model_lang, 'english')
try:
sentence_splitter = nltk_load('tokenizers/punkt/english.pickle')
sentence_splitter = nltk_load(f'tokenizers/punkt_tab/{punkt_lang}.pickle')
except LookupError:
nltk.download('punkt_tab', quiet=True)
sentence_splitter = nltk_load('tokenizers/punkt/english.pickle')
sentence_splitter = nltk_load(f'tokenizers/punkt_tab/{punkt_lang}.pickle')
sentence_spans = list(sentence_splitter.span_tokenize(text))
segment_data[sdx] = {
@@ -223,12 +230,12 @@ def align(
# check we can align
if len(segment_data[sdx]["clean_char"]) == 0:
print(f'Failed to align segment ("{segment["text"]}"): no characters in this segment found in model dictionary, resorting to original...')
logger.warning(f'Failed to align segment ("{segment["text"]}"): no characters in this segment found in model dictionary, resorting to original')
aligned_segments.append(aligned_seg)
continue
if t1 >= MAX_DURATION:
print(f'Failed to align segment ("{segment["text"]}"): original start time longer than audio duration, skipping...')
logger.warning(f'Failed to align segment ("{segment["text"]}"): original start time longer than audio duration, skipping')
aligned_segments.append(aligned_seg)
continue
@@ -270,7 +277,7 @@ def align(
path = backtrack_beam(trellis, emission, tokens, blank_id, beam_width=2)
if path is None:
print(f'Failed to align segment ("{segment["text"]}"): backtrack failed, resorting to original...')
logger.warning(f'Failed to align segment ("{segment["text"]}"): backtrack failed, resorting to original')
aligned_segments.append(aligned_seg)
continue
+10 -6
View File
@@ -12,8 +12,11 @@ from transformers import Pipeline
from transformers.pipelines.pt_utils import PipelineIterator
from whisperx.audio import N_SAMPLES, SAMPLE_RATE, load_audio, log_mel_spectrogram
from whisperx.types import SingleSegment, TranscriptionResult
from whisperx.schema import SingleSegment, TranscriptionResult
from whisperx.vads import Vad, Silero, Pyannote
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
def find_numeral_symbol_tokens(tokenizer):
@@ -247,7 +250,7 @@ class FasterWhisperPipeline(Pipeline):
if self.suppress_numerals:
previous_suppress_tokens = self.options.suppress_tokens
numeral_symbol_tokens = find_numeral_symbol_tokens(self.tokenizer)
print(f"Suppressing numeral and symbol tokens")
logger.info("Suppressing numeral and symbol tokens")
new_suppressed_tokens = numeral_symbol_tokens + self.options.suppress_tokens
new_suppressed_tokens = list(set(new_suppressed_tokens))
self.options = replace(self.options, suppress_tokens=new_suppressed_tokens)
@@ -285,7 +288,7 @@ class FasterWhisperPipeline(Pipeline):
def detect_language(self, audio: np.ndarray) -> str:
if audio.shape[0] < N_SAMPLES:
print("Warning: audio is shorter than 30s, language detection may be inaccurate.")
logger.warning("Audio is shorter than 30s, language detection may be inaccurate")
model_n_mels = self.model.feat_kwargs.get("feature_size")
segment = log_mel_spectrogram(audio[: N_SAMPLES],
n_mels=model_n_mels if model_n_mels is not None else 80,
@@ -294,7 +297,7 @@ class FasterWhisperPipeline(Pipeline):
results = self.model.model.detect_language(encoder_output)
language_token, language_probability = results[0][0]
language = language_token[2:-2]
print(f"Detected language: {language} ({language_probability:.2f}) in first 30s of audio...")
logger.info(f"Detected language: {language} ({language_probability:.2f}) in first 30s of audio")
return language
@@ -319,7 +322,8 @@ def load_model(
whisper_arch - The name of the Whisper model to load.
device - The device to load the model on.
compute_type - The compute type to use for the model.
vad_method - The vad method to use. vad_model has higher priority if is not None.
vad_model - The vad model to manually assign.
vad_method - The vad method to use. vad_model has a higher priority if it is not None.
options - A dictionary of options to use for the model.
language - The language of the model. (use English for now)
model - The WhisperModel instance to use.
@@ -343,7 +347,7 @@ def load_model(
if language is not None:
tokenizer = Tokenizer(model.hf_tokenizer, model.model.is_multilingual, task=task, language=language)
else:
print("No language specified, language will be first be detected for each audio file (increases inference time).")
logger.info("No language specified, language will be detected for each audio file (increases inference time)")
tokenizer = None
default_asr_options = {
+5 -1
View File
@@ -5,7 +5,10 @@ from typing import Optional, Union
import torch
from whisperx.audio import load_audio, SAMPLE_RATE
from whisperx.types import TranscriptionResult, AlignedTranscriptionResult
from whisperx.schema import TranscriptionResult, AlignedTranscriptionResult
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
class DiarizationPipeline:
@@ -18,6 +21,7 @@ class DiarizationPipeline:
if isinstance(device, str):
device = torch.device(device)
model_config = model_name or "pyannote/speaker-diarization-3.1"
logger.info(f"Loading diarization model: {model_config}")
self.model = Pipeline.from_pretrained(model_config, use_auth_token=use_auth_token).to(device)
def __call__(
+67
View File
@@ -0,0 +1,67 @@
import logging
import sys
from typing import Optional
_LOG_FORMAT = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
_DATE_FORMAT = "%Y-%m-%d %H:%M:%S"
def setup_logging(
level: str = "info",
log_file: Optional[str] = None,
) -> None:
"""
Configure logging for WhisperX.
Args:
level: Logging level (debug, info, warning, error, critical). Default: info
log_file: Optional path to log file. If None, logs only to console.
"""
logger = logging.getLogger("whisperx")
logger.handlers.clear()
try:
log_level = getattr(logging, level.upper())
except AttributeError:
log_level = logging.WARNING
logger.setLevel(log_level)
formatter = logging.Formatter(_LOG_FORMAT, datefmt=_DATE_FORMAT)
console_handler = logging.StreamHandler(sys.stdout)
console_handler.setLevel(log_level)
console_handler.setFormatter(formatter)
logger.addHandler(console_handler)
if log_file:
try:
file_handler = logging.FileHandler(log_file)
file_handler.setLevel(log_level)
file_handler.setFormatter(formatter)
logger.addHandler(file_handler)
except (OSError) as e:
logger.warning(f"Failed to create log file '{log_file}': {e}")
logger.warning("Continuing with console logging only")
# Don't propagate to root logger to avoid duplicate messages
logger.propagate = False
def get_logger(name: str) -> logging.Logger:
"""
Get a logger instance for the given module.
Args:
name: Logger name (typically __name__ from calling module)
Returns:
Logger instance configured with WhisperX settings
"""
whisperx_logger = logging.getLogger("whisperx")
if not whisperx_logger.handlers:
setup_logging()
logger_name = "whisperx" if name == "__main__" else name
return logging.getLogger(logger_name)
File renamed without changes.
+12 -9
View File
@@ -10,8 +10,11 @@ from whisperx.alignment import align, load_align_model
from whisperx.asr import load_model
from whisperx.audio import load_audio
from whisperx.diarize import DiarizationPipeline, assign_word_speakers
from whisperx.types import AlignedTranscriptionResult, TranscriptionResult
from whisperx.schema import AlignedTranscriptionResult, TranscriptionResult
from whisperx.utils import LANGUAGES, TO_LANGUAGE_CODE, get_writer
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
def transcribe_task(args: dict, parser: argparse.ArgumentParser):
@@ -103,6 +106,7 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
"no_speech_threshold": args.pop("no_speech_threshold"),
"condition_on_previous_text": False,
"initial_prompt": args.pop("initial_prompt"),
"hotwords": args.pop("hotwords"),
"suppress_tokens": [int(x) for x in args.pop("suppress_tokens").split(",")],
"suppress_numerals": args.pop("suppress_numerals"),
}
@@ -119,7 +123,6 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
# Part 1: VAD & ASR Loop
results = []
tmp_results = []
# model = load_model(model_name, device=device, download_root=model_dir)
model = load_model(
model_name,
@@ -143,7 +146,7 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
for audio_path in args.pop("audio"):
audio = load_audio(audio_path)
# >> VAD & ASR
print(">>Performing transcription...")
logger.info("Performing transcription...")
result: TranscriptionResult = model.transcribe(
audio,
batch_size=batch_size,
@@ -176,13 +179,13 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
if align_model is not None and len(result["segments"]) > 0:
if result.get("language", "en") != align_metadata["language"]:
# load new language
print(
logger.info(
f"New language found ({result['language']})! Previous was ({align_metadata['language']}), loading new alignment model for new language..."
)
align_model, align_metadata = load_align_model(
result["language"], device
)
print(">>Performing alignment...")
logger.info("Performing alignment...")
result: AlignedTranscriptionResult = align(
result["segments"],
align_model,
@@ -204,12 +207,12 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
# >> Diarize
if diarize:
if hf_token is None:
print(
"Warning, no --hf_token used, needs to be saved in environment variable, otherwise will throw error loading diarization model..."
logger.warning(
"No --hf_token provided, needs to be saved in environment variable, otherwise will throw error loading diarization model"
)
tmp_results = results
print(">>Performing diarization...")
print(">>Using model:", diarize_model_name)
logger.info("Performing diarization...")
logger.info(f"Using model: {diarize_model_name}")
results = []
diarize_model = DiarizationPipeline(model_name=diarize_model_name, use_auth_token=hf_token, device=device)
for result, input_audio_path in tmp_results:
+25 -2
View File
@@ -126,6 +126,29 @@ TO_LANGUAGE_CODE = {
LANGUAGES_WITHOUT_SPACES = ["ja", "zh"]
# Mapping of language codes to NLTK Punkt tokenizer model names
PUNKT_LANGUAGES = {
'cs': 'czech',
'da': 'danish',
'de': 'german',
'el': 'greek',
'en': 'english',
'es': 'spanish',
'et': 'estonian',
'fi': 'finnish',
'fr': 'french',
'it': 'italian',
'nl': 'dutch',
'no': 'norwegian',
'pl': 'polish',
'pt': 'portuguese',
'sl': 'slovene',
'sv': 'swedish',
'tr': 'turkish',
"ml": "malayalam",
"ru": "russian",
}
system_encoding = sys.getdefaultencoding()
if system_encoding != "utf-8":
@@ -410,7 +433,7 @@ class WriteJSON(ResultWriter):
def get_writer(
output_format: str, output_dir: str
) -> Callable[[dict, TextIO, dict], None]:
) -> Callable[[dict, str, dict], None]:
writers = {
"txt": WriteTXT,
"vtt": WriteVTT,
@@ -425,7 +448,7 @@ def get_writer(
if output_format == "all":
all_writers = [writer(output_dir) for writer in writers.values()]
def write_all(result: dict, file: TextIO, options: dict):
def write_all(result: dict, file: str, options: dict):
for writer in all_writers:
writer(result, file, options)
+5 -2
View File
@@ -13,6 +13,9 @@ from pyannote.core import Segment
from whisperx.diarize import Segment as SegmentX
from whisperx.vads.vad import Vad
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
def load_vad_model(device, vad_onset=0.500, vad_offset=0.363, use_auth_token=None, model_fp=None):
@@ -232,7 +235,7 @@ class VoiceActivitySegmentation(VoiceActivityDetection):
class Pyannote(Vad):
def __init__(self, device, use_auth_token=None, model_fp=None, **kwargs):
print(">>Performing voice activity detection using Pyannote...")
logger.info("Performing voice activity detection using Pyannote...")
super().__init__(kwargs['vad_onset'])
self.vad_pipeline = load_vad_model(device, use_auth_token=use_auth_token, model_fp=model_fp)
@@ -257,7 +260,7 @@ class Pyannote(Vad):
segments_list.append(SegmentX(speech_turn.start, speech_turn.end, "UNKNOWN"))
if len(segments_list) == 0:
print("No active speech found in audio")
logger.warning("No active speech found in audio")
return []
assert segments_list, "segments_list is empty."
return Vad.merge_chunks(segments_list, chunk_size, onset, offset)
+5 -2
View File
@@ -8,6 +8,9 @@ import torch
from whisperx.diarize import Segment as SegmentX
from whisperx.vads.vad import Vad
from whisperx.log_utils import get_logger
logger = get_logger(__name__)
AudioFile = Union[Text, Path, IOBase, Mapping]
@@ -15,7 +18,7 @@ AudioFile = Union[Text, Path, IOBase, Mapping]
class Silero(Vad):
# check again default values
def __init__(self, **kwargs):
print(">>Performing voice activity detection using Silero...")
logger.info("Performing voice activity detection using Silero...")
super().__init__(kwargs['vad_onset'])
self.vad_onset = kwargs['vad_onset']
@@ -60,7 +63,7 @@ class Silero(Vad):
):
assert chunk_size > 0
if len(segments_list) == 0:
print("No active speech found in audio")
logger.warning("No active speech found in audio")
return []
assert segments_list, "segments_list is empty."
return Vad.merge_chunks(segments_list, chunk_size, onset, offset)