Add docs about using my fork and add more monkey patches

README.md

@@ -8,11 +8,19 @@ This is the model Whisper large-v3 converted to be used in [faster-whisper](http
 
 ## Using
 
+You can choose between monkey-patching faster-whisper 0.9.0 (while they don't update it) or using my fork (which is
+easier).
+
+
+### Using my fork
+
+First, install it by executing:
+
 ```shell
-pip install -U 'faster-whisper>=0.9.0'
+pip install -U 'transformers[torch]>=4.35.0' https://github.com/PythonicCafe/faster-whisper/archive/refs/heads/feature/large-v3.zip#egg=faster-whisper
 ```
 
-Then, you need to monkey patch some parts of the library while there's no new version:
+Then, use it as the regular faster-whisper:
 
 ```python
 import time
@@ -20,27 +28,96 @@ import time
 import faster_whisper
 
 
-faster_whisper.utils._MODELS["large-v3"] = "turicas/faster-whisper-large-v3"  # Monkey patch
-
 filename = "my-audio.mp3"
+initial_prompt = "My podcast recording"  # Or `None`
 word_timestamps = False
 vad_filter = True
 temperature = 0.0
 language = "pt"
 model_size = "large-v3"
-device, compute_type = "cuda", "float16"  # select the desired device, example: "cpu", "float32"
+device, compute_type = "cuda", "float16"
+# or: device, compute_type = "cpu", "float32"
 
 model = faster_whisper.WhisperModel(model_size, device=device, compute_type=compute_type)
-if model_size == "large-v3":  # More monkey patch
-    model.feature_extractor.mel_filters = model.feature_extractor.get_mel_filters(model.feature_extractor.sampling_rate, model.feature_extractor.n_fft, n_mels=128)
 
-# TODO: for some reason it's translating, not transcribing
 segments, transcription_info = model.transcribe(
     filename,
     word_timestamps=word_timestamps,
     vad_filter=vad_filter,
     temperature=temperature,
     language=language,
+    initial_prompt=initial_prompt,
+)
+print(transcription_info)
+
+start_time = time.time()
+for segment in segments:
+    row = {
+        "start": segment.start,
+        "end": segment.end,
+        "text": segment.text,
+    }
+    if word_timestamps:
+        row["words"] = [
+            {"start": word.start, "end": word.end, "word": word.word}
+            for word in segment.words
+        ]
+    print(row)
+end_time = time.time()
+print(f"Transcription finished in {end_time - start_time:.2f}s")
+```
+
+
+### Monkey-patching faster-whisper 0.9.0
+
+Make sure you have the latest version:
+
+```shell
+pip install -U 'faster-whisper>=0.9.0'
+```
+
+Then, use it with some little changes:
+
+```python
+import time
+
+import faster_whisper.transcribe
+
+
+# Monkey patch 1 (add model to list)
+faster_whisper.utils._MODELS["large-v3"] = "turicas/faster-whisper-large-v3"
+
+# Monkey patch 2 (fix Tokenizer)
+faster_whisper.transcribe.Tokenizer.encode = lambda self, text: self.tokenizer.encode(text, add_special_tokens=False)
+
+filename = "my-audio.mp3"
+initial_prompt = "My podcast recording"  # Or `None`
+word_timestamps = False
+vad_filter = True
+temperature = 0.0
+language = "pt"
+model_size = "large-v3"
+device, compute_type = "cuda", "float16"
+# or: device, compute_type = "cpu", "float32"
+
+model = faster_whisper.transcribe.WhisperModel(model_size, device=device, compute_type=compute_type)
+
+# Monkey patch 3 (change n_mels)
+from faster_whisper.feature_extractor import FeatureExtractor
+model.feature_extractor = FeatureExtractor(feature_size=128)
+
+# Monkey patch 4 (change tokenizer)
+from transformers import AutoProcessor
+model.hf_tokenizer = AutoProcessor.from_pretrained("openai/whisper-large-v3").tokenizer
+model.hf_tokenizer.token_to_id = lambda token: model.hf_tokenizer.convert_tokens_to_ids(token)
+
+segments, transcription_info = model.transcribe(
+    filename,
+    word_timestamps=word_timestamps,
+    vad_filter=vad_filter,
+    temperature=temperature,
+    language=language,
+    initial_prompt=initial_prompt,
 )
 print(transcription_info)
 
@@ -76,4 +153,4 @@ Then, the files will be at `whisper-large-v3-ct2/`.
 ## License
 
 These files have the same license as the original [openai/whisper-large-v3
-model](https://huggingface.co/openai/whisper-large): Apache 2.0.
+model](https://huggingface.co/openai/whisper-large): Apache 2.0.